© 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. 107031
    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
     tern
    -0.28
    è´Ł
    -0.28
    empt
    -0.25
    åħį
    -0.24
    é¢Ħ
    -0.24
     ./
    -0.24
    æľ¬æĿ¥
    -0.24
    èIJ¥åķĨ
    -0.24
     affirmative
    -0.24
    upert
    -0.24
    POSITIVE LOGITS
    zenia
    0.31
    urement
    0.29
    acements
    0.27
    меÑīа
    0.26
    issions
    0.26
    æĶ¶èĹı
    0.26
    (Collection
    0.26
    chw
    0.26
    ADM
    0.25
    ynos
    0.25
    Activations Density 4.764%

    No Known Activations

    This feature has no known activations.