© 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. 23276
    Prev
    Next
    INDEX
    Explanations

    World

    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
    å¥ĸåѦéĩij
    -0.33
    è¿Ļ两ç§į
    -0.29
    itin
    -0.29
    (scroll
    -0.26
    ++;č↵
    -0.25
    两ç§į
    -0.25
    çķĭ
    -0.25
    _gradients
    -0.24
    -fw
    -0.24
    _outline
    -0.24
    POSITIVE LOGITS
    ä¸įæĢķ
    0.28
     prove
    0.27
     fooled
    0.26
     blinded
    0.26
     specialize
    0.26
     despite
    0.25
    iy
    0.25
     lump
    0.25
     proved
    0.25
     proven
    0.25
    Activations Density 0.000%

    No Known Activations