© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 22-TRANSCODER-HP
    7. 111110
    Prev
    Next
    INDEX
    Explanations

    Asking the user a question

    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
    Negative Logits
    áb
    -0.31
    earing
    -0.28
    泡
    -0.27
    -find
    -0.26
    ogh
    -0.25
     peaceful
    -0.25
    HttpResponse
    -0.24
    ê°ľ
    -0.24
     вним
    -0.24
    oga
    -0.23
    POSITIVE LOGITS
    ä¸į说
    0.31
    æĬ½åĩº
    0.26
     gettext
    0.25
    çĸĿ
    0.25
    nut
    0.24
    åħļåĨħ
    0.24
     denies
    0.24
    æī«
    0.24
    ży
    0.24
     deny
    0.24
    Activations Density 0.015%

    No Known Activations