© 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. 87776
    Prev
    Next
    INDEX
    Explanations

    programming, medical/scientific texts

    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
    让æĪij们
    -0.26
    intl
    -0.25
    ä¸ij
    -0.25
    	unset
    -0.24
    åĬŀäºĭ
    -0.24
     scar
    -0.23
    èĬ¡
    -0.23
     dak
    -0.23
    çĪ¬
    -0.23
     fort
    -0.23
    POSITIVE LOGITS
    OLID
    0.28
    !*
    0.27
    ogonal
    0.27
    åĨħå¤ĸ
    0.25
    建çŃij设计
    0.25
    å¸ĮæľĽèĥ½
    0.24
    rary
    0.24
    å¾Ĵå¼Ł
    0.23
    arith
    0.23
    ettes
    0.23
    Activations Density 0.001%

    No Known Activations