© 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. 1283
    Prev
    Next
    INDEX
    Explanations

    change, modify, alter, edit

    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
     shaken
    -0.09
    æIJŃ
    -0.09
    满
    -0.09
    ndon
    -0.08
     Cla
    -0.08
    ToPoint
    -0.08
    æ¯Ķè¾ĥ好
    -0.08
    STALL
    -0.08
    atta
    -0.08
    Ñģком
    -0.08
    POSITIVE LOGITS
    æĶ¹åıĺ
    0.17
    æĽ´æĶ¹
    0.16
    ä¿®æĶ¹
    0.15
    éĴĹ
    0.14
    (change
    0.14
    åıĺæĽ´
    0.14
    æĶ¹åĬ¨
    0.14
    æĶ¹è®Ĭ
    0.13
    à¹Ģà¸Ľà¸¥
    0.13
    ç¼ĸè¾ij
    0.13
    Activations Density 0.461%

    No Known Activations