© 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. 112571
    Prev
    Next
    INDEX
    Explanations

    arrest

    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
     Pins
    -0.27
    /API
    -0.26
    åºķä¸ĭ
    -0.24
    å·¥ç¨ĭæĬĢæľ¯
    -0.24
    odos
    -0.23
    rames
    -0.23
    æĸ¼
    -0.23
    /--
    -0.23
    常年
    -0.22
    creasing
    -0.22
    POSITIVE LOGITS
    éĢ®æįķ
    0.29
    衾
    0.28
     seizing
    0.27
    ilk
    0.26
     cuffs
    0.25
     imposition
    0.25
     condition
    0.25
    dale
    0.24
    spr
    0.24
    æĬĵæįķ
    0.24
    Activations Density 0.157%

    No Known Activations