© 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. 63427
    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
    /Test
    -0.25
    ATAB
    -0.24
    ä¹ĭä½ľ
    -0.24
    马åħĭ
    -0.24
    大å¸Ī
    -0.24
    uum
    -0.24
    Experts
    -0.24
    ãĥĽãĥ¼ãĥ«
    -0.24
    ä¸ĵ家
    -0.24
    ÑĮÑİ
    -0.23
    POSITIVE LOGITS
    .sa
    0.29
    elijk
    0.27
    _MEMBER
    0.27
    ->↵
    0.26
    eenth
    0.26
    entina
    0.25
    -ended
    0.25
    âĩ
    0.24
    quarter
    0.24
    owania
    0.24
    Activations Density 16.564%

    No Known Activations

    This feature has no known activations.