© 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. 12-TRANSCODER-HP
    7. 22847
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ç½ij讯
    -0.27
    éłĨ
    -0.24
    _MULTI
    -0.24
    ç®į
    -0.23
    -plane
    -0.23
    HS
    -0.23
    ãģ¤ãģĭ
    -0.23
    ungan
    -0.23
    ãģ£ãģ¡
    -0.23
    -hole
    -0.22
    POSITIVE LOGITS
    rotch
    0.28
    å·¥ä½ľç«Ļ
    0.27
    .ml
    0.26
    %^
    0.25
    让人们
    0.25
    好象
    0.24
    mare
    0.24
    fork
    0.24
    rest
    0.24
    aked
    0.23
    Activations Density 0.000%

    No Known Activations