© 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. 108019
    Prev
    Next
    INDEX
    Explanations

    Actions and activities

    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
    çĩķ
    -0.27
    çīĩéĿ¢
    -0.25
    éĶģå®ļ
    -0.25
    è¾¹éĻħ
    -0.25
     Blackburn
    -0.25
    vers
    -0.24
    çļĦ身ä½ĵ
    -0.24
    å¼ķ导
    -0.24
    é¢Ĩ导人
    -0.24
    两个人
    -0.23
    POSITIVE LOGITS
    _iff
    0.29
    `č↵
    0.25
    HITE
    0.25
    iffin
    0.25
    .Contracts
    0.25
     kre
    0.24
    æݧ
    0.24
     Hicks
    0.24
    `),↵
    0.24
    obe
    0.23
    Activations Density 31.649%

    No Known Activations