© 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. 22624
    Prev
    Next
    INDEX
    Explanations

    luminescence

    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
    aji
    -0.30
    xls
    -0.27
    çªľ
    -0.26
    æĿĤå¿Ĺ社
    -0.26
    å©´
    -0.25
    ulations
    -0.25
    ró
    -0.24
     skl
    -0.24
    ently
    -0.24
    _SYM
    -0.24
    POSITIVE LOGITS
     foss
    0.31
    wa
    0.29
     waived
    0.28
    åħįéĻ¤
    0.27
     egreg
    0.27
     waive
    0.27
     resid
    0.27
    ç»ĻæĪij
    0.27
     geg
    0.27
    het
    0.27
    Activations Density 0.003%

    No Known Activations