© 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. 23121
    Prev
    Next
    INDEX
    Explanations

    stack traces and debugging

    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
    lick
    -0.27
    leases
    -0.25
    eger
    -0.25
    seat
    -0.24
     Male
    -0.24
     czÅĤ
    -0.24
    èħ¥
    -0.24
    _partial
    -0.24
    _MEMBER
    -0.24
    é»İæĺİ
    -0.24
    POSITIVE LOGITS
     SIN
    0.28
    /mainwindow
    0.28
    _hierarchy
    0.28
     planta
    0.27
     sil
    0.27
    è¿«
    0.25
     intermedi
    0.25
    ä¸ĭè½½
    0.25
    ä¸Ĭä¼ł
    0.24
    ä¹Łæľīå¾Īå¤ļ
    0.24
    Activations Density 0.024%

    No Known Activations