© 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. 22-TRANSCODER-HP
    7. 88090
    Prev
    Next
    INDEX
    Explanations

    acceptable/fine

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    (DE
    -0.27
    é«ĺä½į
    -0.27
    ç¢İ
    -0.25
    _warnings
    -0.25
     manh
    -0.24
    æ¬ł
    -0.24
    /plugins
    -0.24
     thừa
    -0.24
    _fragment
    -0.24
    cence
    -0.24
    POSITIVE LOGITS
    wiki
    0.27
    è¿Ľè¡Į
    0.27
    è¿Ľè¡Įåħ¨éĿ¢
    0.27
     webs
    0.25
     sod
    0.25
    èĭ£
    0.24
    _ATTR
    0.23
    lobber
    0.23
    urs
    0.23
    åŁ
    0.23
    Activations Density 0.028%

    No Known Activations