© 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. 48989
    Prev
    Next
    INDEX
    Explanations

    LEGO plays

    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
    è½»æĺĵ
    -0.09
     ìĿ´ë£¨
    -0.08
    ponder
    -0.08
    ust
    -0.08
    åħ³éĶ®æŶåĪ»
    -0.08
    kok
    -0.08
    или
    -0.08
    -plugins
    -0.08
    sing
    -0.08
    ypad
    -0.08
    POSITIVE LOGITS
    åĦ¿
    0.11
    ÅĪ
    0.10
    çİĭåĽ½
    0.10
    åĻ±
    0.09
    ä¸įéĶĪ
    0.09
    å±ij
    0.09
    çĽ¸ä¼´
    0.09
    ç»ı纬
    0.09
    åħ¨æĹ¥
    0.09
    榫
    0.09
    Activations Density 0.001%

    No Known Activations