© 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. 63588
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    jid
    -0.28
    æ¶ĪéĻ¤
    -0.25
     awaiting
    -0.25
    说äºĨ
    -0.25
     lookout
    -0.25
    ä½ľåĩºäºĨ
    -0.24
     imposes
    -0.24
    åŀĽ
    -0.24
    ç¨³åĽº
    -0.24
    æĿľç»Ŀ
    -0.24
    POSITIVE LOGITS
    广
    0.28
    inth
    0.28
    æ°´å¹³
    0.26
    èı²
    0.26
    rogen
    0.25
    abeth
    0.25
    pheres
    0.25
    大èĥĨ
    0.25
    çĶŁæ´»çļĦ
    0.25
    çģ«
    0.25
    Activations Density 23.798%

    No Known Activations

    This feature has no known activations.