© 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. 107843
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    æľ¬ç½ij
    -0.27
    ç»ıå¼Ģ
    -0.25
     Constitutional
    -0.25
     unconscious
    -0.24
    ä¹ı
    -0.24
    oter
    -0.23
    uits
    -0.23
    åľ°ä¸Ĭ
    -0.23
    NDER
    -0.23
    itr
    -0.23
    POSITIVE LOGITS
    toa
    0.28
    æľ¬è½®
    0.26
    ë°
    0.26
    OLF
    0.25
    antino
    0.25
    .rawValue
    0.25
    greSQL
    0.24
    веÑģ
    0.24
    ä»ĸ表示
    0.24
    ()(
    0.23
    Activations Density 3.552%

    No Known Activations

    This feature has no known activations.