© 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. 30-TRANSCODER-HP
    7. 95373
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     suppl
    -0.25
    endon
    -0.24
     tort
    -0.24
    è°Ĭ
    -0.24
    plorer
    -0.23
    èŀįåIJĪ
    -0.23
     khảo
    -0.23
    ç½ijåIJ§
    -0.23
     Maher
    -0.23
    ramid
    -0.23
    POSITIVE LOGITS
    unds
    0.28
    ä½łä»¬
    0.26
    lemn
    0.26
    (ord
    0.26
    æĹ¥åĩĮæĻ¨
    0.25
    oded
    0.25
    åĪĩãĤĬ
    0.24
     spot
    0.24
    ģını
    0.24
     {
    0.24
    Activations Density 0.938%

    No Known Activations

    This feature has no known activations.