© 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. 31-TRANSCODER-HP
    7. 18057
    Prev
    Next
    INDEX
    Explanations

    people

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_31.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.31.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    holm
    -0.35
     respons
    -0.33
    respons
    -0.32
    责任
    -0.31
     responsibility
    -0.31
    iqueta
    -0.28
     crochet
    -0.26
     responsible
    -0.26
     responsable
    -0.26
    ánh
    -0.26
    POSITIVE LOGITS
     connected
    0.41
     engaged
    0.39
    -connected
    0.34
    connected
    0.33
     Connected
    0.31
     involved
    0.28
    Connected
    0.28
    -visible
    0.28
     retained
    0.28
    ä¹Ŀåįģ
    0.27
    Activations Density 2.211%

    No Known Activations