© 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. 23290
    Prev
    Next
    INDEX
    Explanations

    which

    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
    -await
    -0.25
    ãģ¤ãģĦ
    -0.25
     walls
    -0.25
    éģģ
    -0.24
     specializing
    -0.24
    agan
    -0.24
    ocode
    -0.23
    tables
    -0.23
    ä¸ĢéĿ¢
    -0.23
     Keyboard
    -0.23
    POSITIVE LOGITS
    xis
    0.31
     baÅŁka
    0.26
    .bpm
    0.25
    æĭīæĸ¯
    0.25
    SSI
    0.25
    rol
    0.25
    足
    0.24
    SI
    0.23
     loosely
    0.23
    çĻĥ
    0.23
    Activations Density 0.002%

    No Known Activations