© 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. 95778
    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
     ((__
    -0.29
    åĿŁ
    -0.28
     века
    -0.27
    tom
    -0.26
    æľ¬åľ°
    -0.26
     times
    -0.25
    ç©¿
    -0.24
    records
    -0.24
    itzer
    -0.24
    ((__
    -0.24
    POSITIVE LOGITS
    getParam
    0.28
    æķ£
    0.26
     Wolfgang
    0.25
    çĶŁèĤĸ
    0.25
    shine
    0.24
    sein
    0.24
    è°¢
    0.24
    æ°ijçĶŁ
    0.24
    åħ¨æĹ¥åĪ¶
    0.23
     phóng
    0.23
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.