© 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. 112826
    Prev
    Next
    INDEX
    Explanations

    Mot

    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
     birthday
    -0.27
    reen
    -0.26
    éĺ¿å§¨
    -0.25
     letter
    -0.25
     flex
    -0.24
     answers
    -0.24
    å·¡
    -0.23
    amble
    -0.23
     man
    -0.23
     letters
    -0.23
    POSITIVE LOGITS
    subclass
    0.29
    主ä¹īæĢĿæĥ³
    0.26
    WhatsApp
    0.25
     Weiner
    0.25
    .gradient
    0.25
    诼
    0.25
    Stick
    0.25
    oksen
    0.25
    æĶĢ
    0.23
    说æ³ķ
    0.23
    Activations Density 0.004%

    No Known Activations