© 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. 15-RESID-POST-AA
    11. 48213
    Prev
    Next
    INDEX
    Explanations

    ASCII art

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    巧克力
    -0.09
    ɐ
    -0.08
    缙
    -0.08
     Volkswagen
    -0.07
     świ
    -0.07
    constexpr
    -0.07
     paralle
    -0.07
    .capitalize
    -0.07
    ogr
    -0.07
     slang
    -0.06
    POSITIVE LOGITS
    gest
    0.07
    motor
    0.07
    عاد
    0.07
    olding
    0.07
    aset
    0.07
    ệm
    0.07
    pción
    0.07
     włos
    0.07
    finding
    0.07
    unts
    0.06
    Activations Density 0.029%

    No Known Activations