© 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. 129601
    Prev
    Next
    INDEX
    Explanations

    This

    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
    åľ¨ä»ĸ
    -0.31
    åľ¨ä»ĸçļĦ
    -0.29
    his
    -0.28
    His
    -0.27
     nam
    -0.26
    åľ¨éĤ£éĩĮ
    -0.24
    äºĨä»ĸçļĦ
    -0.24
     His
    -0.23
    .RecyclerView
    -0.23
     his
    -0.23
    POSITIVE LOGITS
     hurt
    0.27
     dispro
    0.26
     Gross
    0.26
    descr
    0.26
    -Cs
    0.25
    orange
    0.25
    -CS
    0.25
    éľĩæħij
    0.24
    Bes
    0.23
    pNet
    0.23
    Activations Density 21.568%

    No Known Activations