© 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. 56637
    Prev
    Next
    INDEX
    Explanations

    finishing positions (e.g., third, fourth)

    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
    å¾Ģå¤ĸ
    -0.10
    æĬĬå®ĥ
    -0.09
    çļĦçľ¼åħī
    -0.09
    çļĦåģļæ³ķ
    -0.09
    æħ¢æħ¢åľ°
    -0.09
    aus
    -0.08
    æħ¢æħ¢
    -0.08
    åįĬ天
    -0.08
    çİ©æ³ķ
    -0.08
    æŁ¥çľĭæĽ´å¤ļ
    -0.08
    POSITIVE LOGITS
    ãĤ¹ãĤŃ
    0.11
    骥
    0.10
    ={({
    0.10
    åįĹå±±
    0.09
    ä¸įåĪĨ
    0.09
    XObject
    0.09
    argent
    0.09
    _DL
    0.09
    éªħ
    0.08
    йÑĤ
    0.08
    Activations Density 0.024%

    No Known Activations