© 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. 12-TRANSCODER-HP
    7. 21939
    Prev
    Next
    INDEX
    Explanations

    Legal/court documents

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    骧
    -0.28
    çļĦå°±æĺ¯
    -0.26
     Dil
    -0.25
    çŃīåĢĻ
    -0.25
    !("{
    -0.24
     fit
    -0.24
    é¢Ĩ导ä¸ĭ
    -0.23
    è´²
    -0.23
     wom
    -0.23
     nec
    -0.23
    POSITIVE LOGITS
    æŃĮ
    0.29
    _ET
    0.28
    aille
    0.26
    laps
    0.26
    HCI
    0.25
    repid
    0.24
    ange
    0.24
    assy
    0.24
    profession
    0.24
    好äºĭ
    0.24
    Activations Density 0.001%

    No Known Activations