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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 20-TRANSCODER-HP
    7. 64032
    Prev
    Next
    INDEX
    Explanations

    Programming code and languages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cloth
    -0.26
    ToFit
    -0.26
    bson
    -0.26
    =DB
    -0.25
    åľ¨åŃ¦æł¡
    -0.25
    çľģæķĻèĤ²
    -0.25
    iversary
    -0.25
    ãģĦãģĨ
    -0.24
    åĬ¨äºº
    -0.24
    éĢĤåIJĪèĩªå·±
    -0.24
    POSITIVE LOGITS
     followed
    0.35
    以åıĬ
    0.35
     AND
    0.34
    ))+
    0.32
    æĢ§åĴĮ
    0.30
     &&č↵
    0.29
    itur
    0.29
    ])+
    0.29
    ãĢģ
    0.27
    åĪ©çĶ¨çİĩ
    0.27
    Activations Density 34.448%

    No Known Activations