© 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. 111566
    Prev
    Next
    INDEX
    Explanations

    computer code/technical documentation

    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
    -Origin
    -0.28
    uforia
    -0.27
    åIJĦæł·
    -0.25
     sla
    -0.25
    éĸ±
    -0.24
    aeda
    -0.24
    -Aug
    -0.24
    èµŃ
    -0.23
    ToFront
    -0.23
    rael
    -0.23
    POSITIVE LOGITS
    æĭĴç»Ŀ
    0.29
     pouch
    0.27
    ä¸Ģ个å°ı
    0.25
    :message
    0.25
    éĢļçŁ¥ä¹¦
    0.25
    itter
    0.24
    ARING
    0.24
    person
    0.24
    scient
    0.24
    åIJįä¹ī
    0.23
    Activations Density 0.001%

    No Known Activations