© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 19-RESID-POST-AA
    6. 75711
    Prev
    Next
    INDEX
    Explanations

    chess moves

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    微商
    -0.07
     Trader
    -0.07
    ᒡ
    -0.07
    ခ
    -0.07
     Pé
    -0.07
    .Classes
    -0.07
    宝鸡
    -0.07
     populations
    -0.07
     Plants
    -0.07
    Intermediate
    -0.07
    POSITIVE LOGITS
    /gr
    0.07
     futile
    0.07
    기간
    0.07
     configuration
    0.07
     /*
    0.07
     searched
    0.07
    燃料
    0.07
     nearer
    0.07
    🐛
    0.07
     didnt
    0.06
    Activations Density 0.011%

    No Known Activations