© 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. 20-TRANSCODER-HP
    7. 63619
    Prev
    Next
    INDEX
    Explanations

    lacks a clear theme

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ibs
    -0.27
    ammed
    -0.26
    æŁ¥çľĭæĽ´å¤ļ
    -0.25
    ãĤĪãģĨãģ«
    -0.25
     Kit
    -0.25
     Slot
    -0.24
    å±ij
    -0.24
    ä¼ļå½±åĵį
    -0.24
    æİĴ
    -0.24
    etus
    -0.24
    POSITIVE LOGITS
    åºĸ
    0.30
    DbType
    0.27
    èĬĤ
    0.26
    onest
    0.25
    æ²ī
    0.25
    [:,:,
    0.24
    åĿį
    0.24
    è¿Ń代
    0.23
     tonic
    0.23
    SelfPermission
    0.23
    Activations Density 16.196%

    No Known Activations