© 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. 63307
    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
    wij
    -0.28
    èĩªåĬ©
    -0.28
    urette
    -0.26
    IQUE
    -0.26
     uncert
    -0.26
    ADO
    -0.26
    nesc
    -0.26
    -haired
    -0.25
    Dou
    -0.25
    nicos
    -0.25
    POSITIVE LOGITS
    æĿ¥ä¸įåıĬ
    0.28
     f
    0.27
    utations
    0.26
    f
    0.26
     pastoral
    0.25
     Ethi
    0.24
    å¼ĭ
    0.24
    plied
    0.24
    esity
    0.24
    æĸĩ娱
    0.23
    Activations Density 30.742%

    No Known Activations

    This feature has no known activations.