© 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. 30-TRANSCODER-HP
    7. 94888
    Prev
    Next
    INDEX
    Explanations

    Staff

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    被æīĵ
    -0.30
    itect
    -0.29
    ä¸Ģå°ģä¿¡
    -0.29
    ighth
    -0.27
     Dabei
    -0.26
    flat
    -0.26
    ä¸ĢéĹ´
    -0.26
    ä¸Ģä¸Ŀ
    -0.25
    toMatch
    -0.25
    æİĸ
    -0.25
    POSITIVE LOGITS
    èģĮåijĺ
    0.43
    å·¥ä½ľäººåijĺ
    0.36
     staff
    0.34
     collaborators
    0.34
    Staff
    0.33
     personnel
    0.32
     analysts
    0.31
     employees
    0.31
    staff
    0.31
    åijĺå·¥
    0.31
    Activations Density 0.888%

    No Known Activations