© 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. 31121
    Prev
    Next
    INDEX
    Explanations

    proper nouns

    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
    å¥¹åľ¨
    -0.09
    ä¹ŁæĪIJ为
    -0.08
    ä»ĸä»¬åľ¨
    -0.08
    aval
    -0.08
    è¯¥æł¡
    -0.08
    ç¾İåĨĽ
    -0.08
    该åİ¿
    -0.08
    æĹłå¥Ī
    -0.08
    娣
    -0.08
    ike
    -0.08
    POSITIVE LOGITS
    æĺ¯æĪijçļĦ
    0.11
    éĢŃ
    0.10
    ä¿¡ç®±
    0.09
    è¿Ļæł·ä¸Ģ
    0.09
    Ñģкоп
    0.09
    плав
    0.09
     мо
    0.09
    æĪijå°±
    0.09
    åĽłä¸ºæĪij
    0.09
    issy
    0.09
    Activations Density 0.072%

    No Known Activations