© 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. 290
    Prev
    Next
    INDEX
    Explanations

    >

    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
     Pett
    -0.07
    'Brien
    -0.07
    蓁
    -0.07
    ؼ
    -0.07
     этих
    -0.07
     upset
    -0.06
    Raw
    -0.06
    //{↵
    -0.06
     Road
    -0.06
    aras
    -0.06
    POSITIVE LOGITS
     cache
    0.07
    BTC
    0.07
     snapchat
    0.07
     UID
    0.06
    orrent
    0.06
    дрес
    0.06
    _STRING
    0.06
    istory
    0.06
     בינלאומי
    0.06
    outube
    0.06
    Activations Density 0.036%

    No Known Activations