© 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. 62603
    Prev
    Next
    INDEX
    Explanations

    protection

    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
    摆在
    -0.07
    -do
    -0.07
    纠正
    -0.07
    Ram
    -0.06
     Grim
    -0.06
    演
    -0.06
    醫生
    -0.06
    >You
    -0.06
    的积极性
    -0.06
     Description
    -0.06
    POSITIVE LOGITS
    _ipv
    0.08
    鲥
    0.08
    縻
    0.08
     hugged
    0.07
     closure
    0.07
    hpp
    0.07
    OnUiThread
    0.07
     tasty
    0.07
    芴
    0.07
    lpVtbl
    0.07
    Activations Density 0.008%

    No Known Activations