© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 101
    Prev
    Next
    INDEX
    Explanations

    Listening to feedback

    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
    (unittest
    -0.07
     decoded
    -0.06
    UGIN
    -0.06
     pledge
    -0.06
    Come
    -0.06
    	no
    -0.06
     related
    -0.06
    从未
    -0.06
     positive
    -0.06
    [:]
    -0.06
    POSITIVE LOGITS
    /__
    0.07
     תמ
    0.07
     trois
    0.06
     eigenen
    0.06
     vouchers
    0.06
    委员
    0.06
     pesquisa
    0.06
    騰
    0.06
     mão
    0.06
    กา
    0.06
    Activations Density 0.088%

    No Known Activations