© 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. 27-TRANSCODER-HP
    7. 9717
    Prev
    Next
    INDEX
    Explanations

    People and their history

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    çķª
    -0.28
    åĩıå°ij
    -0.27
    åijĺ
    -0.27
    å¾Īå¥½åľ°
    -0.26
    åĩıè½»
    -0.25
     seller
    -0.25
    Feed
    -0.24
    äºĭåĬ¡
    -0.24
    åĽĽæĺ¯
    -0.24
    клон
    -0.24
    POSITIVE LOGITS
     arrived
    0.27
    oscope
    0.27
    åķIJ
    0.25
    å¾ħãģ¡
    0.25
    riendly
    0.25
    åħ¥å¢ĥ
    0.25
     subscribed
    0.25
    atform
    0.24
     himself
    0.23
    vak
    0.23
    Activations Density 0.001%

    No Known Activations