© 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. 88115
    Prev
    Next
    INDEX
    Explanations

    Medical/anatomical

    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
    andre
    -0.29
    HIR
    -0.26
    CID
    -0.25
    bject
    -0.25
    atial
    -0.24
    åİĨåı²æĢ§
    -0.24
    æīĢåľ¨
    -0.24
    eliness
    -0.24
     Ding
    -0.24
    ACES
    -0.24
    POSITIVE LOGITS
    åı£å¾Ħ
    0.27
    OperationException
    0.26
    itary
    0.25
    è°¤
    0.25
    .Mapper
    0.24
    åIJįèªī
    0.24
     Laugh
    0.23
    é¢Ī
    0.23
    urai
    0.23
    ä¹Łå¥½
    0.23
    Activations Density 0.055%

    No Known Activations