© 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. 22494
    Prev
    Next
    INDEX
    Explanations

    Technical/scientific publications

    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
    istence
    -0.30
     issue
    -0.28
    è®°å¿Ĩ
    -0.27
    ments
    -0.27
    QRS
    -0.27
    htags
    -0.26
    losion
    -0.25
    éĵ¾æĿ¡
    -0.25
    Chart
    -0.25
    è®°å¿ĨåĬĽ
    -0.24
    POSITIVE LOGITS
    çĽ¸äº²
    0.26
    ampo
    0.26
    perial
    0.24
     Lik
    0.24
    ataka
    0.24
    天æĸĩ
    0.24
     Daemon
    0.24
     Grab
    0.23
     Teacher
    0.23
    scenes
    0.23
    Activations Density 0.007%

    No Known Activations