© 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. 3252
    Prev
    Next
    INDEX
    Explanations

    wrestling promotions and events

    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
     ëĤĺëĬĶ
    -0.09
    è¿¥
    -0.09
    客æ°Ķ
    -0.08
    è¾¹éĻħ
    -0.08
    订éĺħ
    -0.08
    ä¸ĵä¸ļ人士
    -0.08
    جز
    -0.08
    è°´
    -0.08
    åı¯éĿł
    -0.08
    Ź
    -0.08
    POSITIVE LOGITS
    æ¾Ħæ¸ħ
    0.10
    å¼ķ
    0.10
    髯
    0.10
     Decay
    0.09
    decay
    0.09
    æĮijè¡ħ
    0.09
    çł´åĿı
    0.09
    isol
    0.09
    çŃĸåĪĴ
    0.09
    èĩ
    0.09
    Activations Density 0.039%

    No Known Activations