© 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. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 47958
    Prev
    Next
    INDEX
    Explanations

    line or continuous

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    éĸĭæĶ¾
    -0.10
    å¼ĢæĶ¾
    -0.10
    çŁ¥å·±
    -0.09
     manifest
    -0.09
    å±ĢéĿ¢
    -0.09
     face
    -0.08
    æĬķæľº
    -0.08
    éĿ¢
    -0.08
    èµ·æŃ¥
    -0.08
    _face
    -0.08
    POSITIVE LOGITS
     chain
    0.13
    éĵ¾æĿ¡
    0.13
     lineage
    0.11
    轨迹
    0.11
    CHAIN
    0.11
    -chain
    0.11
    chain
    0.11
    éĵ¾
    0.11
    èĦī
    0.10
    çĽ¸ä¼ł
    0.10
    Activations Density 0.210%

    No Known Activations