© 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. 63233
    Prev
    Next
    INDEX
    Explanations

    questions

    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
    å°±å¿ħé¡»
    -0.30
    oplayer
    -0.30
    _blocking
    -0.25
     Detailed
    -0.25
    sheets
    -0.25
    conduct
    -0.24
    çļĦåħ³éĶ®
    -0.24
    ibold
    -0.24
     ned
    -0.23
    bon
    -0.23
    POSITIVE LOGITS
     fact
    0.27
    æĪIJ为ä¸ŃåĽ½
    0.25
    åĨĪ
    0.25
    ing
    0.24
    åľ¨ä¸ŃåĽ½
    0.24
    VERR
    0.24
     equivalent
    0.24
    æĥ³è±¡åĬĽ
    0.23
    è¡ĮåĪĹ
    0.23
    anga
    0.23
    Activations Density 38.204%

    No Known Activations