© 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. 35395
    Prev
    Next
    INDEX
    Explanations

    forecast

    np_max-act · gemini-2.0-flash
    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
     iP
    -0.07
    uuid
    -0.07
    _submission
    -0.07
    𝑑
    -0.07
    走访
    -0.07
    要做到
    -0.07
     vampire
    -0.07
    �
    -0.07
    ')(
    -0.07
    POSITIVE LOGITS
    计划
    0.09
     mechan
    0.07
    _FIN
    0.07
    Administrator
    0.07
     практичес
    0.07
    ское
    0.07
    سياسات
    0.07
    _pcm
    0.07
    儿科
    0.07
    _picker
    0.07
    Activations Density 0.004%

    No Known Activations