© 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. 25-TRANSCODER-HP
    7. 109518
    Prev
    Next
    INDEX
    Explanations

    comma

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    æľĢ好
    -0.27
     Pars
    -0.26
    loud
    -0.26
     Scri
    -0.26
    串
    -0.25
    omy
    -0.25
     truthful
    -0.25
    âĤ¹
    -0.25
    liest
    -0.24
    lob
    -0.24
    POSITIVE LOGITS
    沿线
    0.26
    è·¯å¾Ħ
    0.26
    è¿ĻéĩĮæĺ¯
    0.26
    åŁĥå°Ķ
    0.26
    ymes
    0.25
    è¿Ļä¹Īå¤ļå¹´
    0.25
    æīįè¡Į
    0.25
     face
    0.25
    andise
    0.25
     mo
    0.24
    Activations Density 0.915%

    No Known Activations