Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 127740
    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_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
     możliwości
    -0.07
    导入
    -0.07
     demographics
    -0.07
    ignite
    -0.07
    .Toggle
    -0.07
     EITHER
    -0.07
    當您
    -0.07
    agner
    -0.06
    ез
    -0.06
    allele
    -0.06
    POSITIVE LOGITS
    enerate
    0.07
    ҽ
    0.07
     cout
    0.07
     قوله
    0.07
    /*↵
    0.06
    arti
    0.06
     fiery
    0.06
     lui
    0.06
    _run
    0.06
     LIMIT
    0.06
    Activations Density 0.054%

    No Known Activations