© 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. 64288
    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
    å·§åIJĪ
    -0.27
    ä¸ªå·¥ä½ľæĹ¥
    -0.27
     Citizen
    -0.26
     {{↵
    -0.26
     pooling
    -0.25
    GENCY
    -0.24
    лав
    -0.24
    Mov
    -0.24
    太快
    -0.23
    _ctr
    -0.23
    POSITIVE LOGITS
    泡
    0.27
     nut
    0.27
    çİ°ä»»
    0.26
     rel
    0.25
    argo
    0.25
    åIJĪä½ľ
    0.25
    multipart
    0.24
    éĢļ车
    0.24
    ãĢĬ
    0.24
    æĦŁè§ī
    0.24
    Activations Density 7.355%

    No Known Activations

    This feature has no known activations.