© 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. 7-RESID-POST-AA
    6. 102559
    Prev
    Next
    INDEX
    Explanations

    Code

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    slope
    -0.07
     cocks
    -0.07
    表面
    -0.07
     haha
    -0.07
    zoek
    -0.07
    Attempting
    -0.06
    itably
    -0.06
    ('"
    -0.06
     speedy
    -0.06
    そ
    -0.06
    POSITIVE LOGITS
    筲
    0.08
     narzędzi
    0.08
    ชำระ
    0.07
     pacientes
    0.07
    焌
    0.07
    גלגל
    0.06
    .openg
    0.06
    era
    0.06
     ({↵
    0.06
     NSInteger
    0.06
    Activations Density 0.103%

    No Known Activations