© 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. 141553
    Prev
    Next
    INDEX
    Explanations

    stop words

    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
    è®¤çľŁåŃ¦ä¹ł
    -0.33
     pomp
    -0.28
     preached
    -0.25
    ÑĤика
    -0.25
    olicy
    -0.24
     patience
    -0.24
    è®¤çľŁ
    -0.24
    ä½ĵåĬĽ
    -0.24
     znal
    -0.23
    åĨ³èµĽ
    -0.23
    POSITIVE LOGITS
     automatic
    0.43
     automatically
    0.39
    èĩªåĬ¨
    0.37
    -automatic
    0.35
    automatic
    0.35
     instant
    0.35
     automated
    0.34
    çĶµèĦij
    0.32
    æĺ¾ç¤º
    0.32
    èĩªåĭķ
    0.32
    Activations Density 45.341%

    No Known Activations