© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 109811
    Prev
    Next
    INDEX
    Explanations

    technical discussions

    np_max-act · gemini-2.0-flash

    The neuron detects capitalized name-like tokens (proper names, product/usernames, or CamelCase/Title-style segments).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    🍌
    -0.07
    ользоват
    -0.07
     weighed
    -0.06
     MutableLiveData
    -0.06
    숩
    -0.06
    (th
    -0.06
    fffffff
    -0.06
    .key
    -0.06
    log
    -0.06
    鹬
    -0.06
    POSITIVE LOGITS
     Margaret
    0.07
    protect
    0.07
    APH
    0.07
    _CA
    0.07
     Cascade
    0.07
    .axes
    0.07
     indicator
    0.07
     Carnegie
    0.07
     której
    0.07
     теперь
    0.07
    Activations Density 0.034%

    No Known Activations