© 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. 32377
    Prev
    Next
    INDEX
    Explanations

    scientific peer-reviewed literature

    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
    绸
    -0.11
    oret
    -0.10
    åij³
    -0.09
    à¸Ħม
    -0.09
    è¶ħé«ĺ
    -0.09
     rough
    -0.09
    å·´å·´
    -0.09
    åĨľåī¯äº§åĵģ
    -0.09
    æ¯ıä½į
    -0.09
    æµģçķħ
    -0.09
    POSITIVE LOGITS
    ç§ijçłĶ
    0.12
     peer
    0.11
    ç§ijåѦ
    0.10
    ç§ijåŃ¦å®¶
    0.10
     scientists
    0.09
    ç§ijåѦçłĶ究
    0.09
    peer
    0.09
    éĴ»çłĶ
    0.09
     scientist
    0.09
     scientific
    0.09
    Activations Density 0.302%

    No Known Activations