© 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. 4151
    Prev
    Next
    INDEX
    Explanations

    how sensitive or consistent something is

    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
    çĶļ
    -0.11
    æ³¾
    -0.09
    修身
    -0.09
    èĻ¬
    -0.08
    slack
    -0.08
    åĽłä¸ºæĪij们
    -0.08
    ä¸ŃéĢĶ
    -0.08
    çİĩè¾¾
    -0.08
    ált
    -0.08
    å¥ī
    -0.08
    POSITIVE LOGITS
    çļĦä¸Ģç§į
    0.12
    çļĦä¸ĢéĿ¢
    0.09
    ãģĦãģĭ
    0.09
    èķĻ
    0.09
     ìĸ¼ë§ĪëĤĺ
    0.09
    Coll
    0.09
    该项
    0.09
    ä¸Ģ个人
    0.09
    enko
    0.08
    ARI
    0.08
    Activations Density 0.227%

    No Known Activations