© 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. 58613
    Prev
    Next
    INDEX
    Explanations

    drink

    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
    andard
    -0.25
    {*
    -0.25
    äm
    -0.24
    urnished
    -0.24
    _OC
    -0.23
    anie
    -0.23
     {*
    -0.23
    èݽ
    -0.22
    è¡Ķ
    -0.22
    ressed
    -0.22
    POSITIVE LOGITS
    INGS
    0.25
    spot
    0.24
    ä¸ŃæľĢ
    0.24
     strip
    0.23
    sville
    0.23
     Stop
    0.23
    iness
    0.22
    ç½ijåıĭè¯Ħ论
    0.22
     IPAddress
    0.22
    SAFE
    0.22
    Activations Density 0.116%

    No Known Activations