© 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. 107578
    Prev
    Next
    INDEX
    Explanations

    Ability to do something

    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
    åīįæīĢ
    -0.33
     pouvoir
    -0.31
    usk
    -0.30
    åı¯ä»¥æĬĬ
    -0.30
    LEG
    -0.29
    æĤ¨åı¯ä»¥
    -0.27
    åı¯ä»¥
    -0.27
     pouvez
    -0.27
    åı¯ä»¥æł¹æį®
    -0.26
     poder
    -0.26
    POSITIVE LOGITS
    yll
    0.28
     Esper
    0.27
    ç¯ĩ
    0.26
    EObject
    0.26
     til
    0.25
    Ion
    0.25
    mpp
    0.24
     Zelda
    0.24
    Pel
    0.24
    å½ĵçĦ¶æĺ¯
    0.24
    Activations Density 50.647%

    No Known Activations