© 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. 141095
    Prev
    Next
    INDEX
    Explanations

    Web snippets

    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
    FFF
    -0.27
    missive
    -0.26
    alia
    -0.26
    èµĦæºIJæķ´åIJĪ
    -0.24
    ׳×ķת
    -0.24
    inan
    -0.24
    ä¸įåģľ
    -0.24
     classy
    -0.24
    .Focus
    -0.24
    åĴ¨
    -0.24
    POSITIVE LOGITS
    atore
    0.27
    çIJ´
    0.27
    (each
    0.26
     barrel
    0.25
    åĪĴåĪĨ
    0.25
    å¼¥
    0.24
    åŃIJå¼¹
    0.24
     reproduction
    0.24
    ADOS
    0.24
    åŃIJ
    0.23
    Activations Density 59.717%

    No Known Activations