© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 12-TRANSCODER-HP
    7. 22889
    Prev
    Next
    INDEX
    Explanations

    pair

    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
    Not in Any Lists

    No Comments

    Negative Logits
    夫妻
    -0.34
    åıĮæĸ¹
    -0.31
    亲åŃIJ
    -0.31
    é»ĺå¥ij
    -0.31
     Sharing
    -0.31
     partnership
    -0.30
    åIJĪä¼Ļ
    -0.30
    ä¼ī
    -0.30
     shared
    -0.29
     joint
    -0.29
    POSITIVE LOGITS
     fier
    0.28
     Intellectual
    0.26
    .bd
    0.26
    olon
    0.26
    é³ŀ
    0.26
    fad
    0.25
    -meta
    0.25
     deadliest
    0.25
     fen
    0.24
    avo
    0.24
    Activations Density 0.002%

    No Known Activations