© 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. 22-TRANSCODER-HP
    7. 98581
    Prev
    Next
    INDEX
    Explanations

    make

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Chall
    -0.26
    æĬĵæįķ
    -0.25
    atement
    -0.25
    глав
    -0.25
     exactly
    -0.24
     Jab
    -0.24
     Shack
    -0.24
     Ster
    -0.23
    راء
    -0.23
    quat
    -0.23
    POSITIVE LOGITS
    为人
    0.25
    _NC
    0.24
    ç¾İåĽ½
    0.24
    OfWork
    0.24
    ofs
    0.23
    æ¯ķ
    0.23
    ofday
    0.23
     traveller
    0.23
     America
    0.23
    çľĭ好
    0.23
    Activations Density 0.007%

    No Known Activations