© 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. 107853
    Prev
    Next
    INDEX
    Explanations

    Film

    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
    amation
    -0.26
    ienie
    -0.25
    iena
    -0.25
     Ñĩа
    -0.25
    lab
    -0.25
    åĮĸçļĦ
    -0.24
    èŀ¯
    -0.24
    chai
    -0.24
    raz
    -0.24
    orgia
    -0.24
    POSITIVE LOGITS
    æ£ł
    0.28
    hek
    0.28
     blown
    0.24
     Geh
    0.24
     persisted
    0.24
    assy
    0.24
    åıijå±ķæĪĺçķ¥
    0.24
    ç»ıèIJ¥æ¨¡å¼ı
    0.23
    Fcn
    0.23
     profound
    0.23
    Activations Density 52.157%

    No Known Activations