© 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. 1164
    Prev
    Next
    INDEX
    Explanations

    or withdrawal

    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
    æŃ£éĿ¢
    -0.10
    ä¹±
    -0.10
     Kron
    -0.09
     bypass
    -0.09
    acji
    -0.09
    éĵŃ
    -0.09
    reuse
    -0.09
    å°Ŀ
    -0.09
    已被
    -0.09
    å¼¯æĽ²
    -0.09
    POSITIVE LOGITS
    éļıæŶ
    0.17
    éļ¨æĻĤ
    0.14
    ä¸ŃéĢĶ
    0.12
    ä»»ä½ķæŶåĢĻ
    0.12
    ç»ĪæŃ¢
    0.11
    åıĹä¸įäºĨ
    0.09
    ä¸į满æĦı
    0.09
    æĴ¤éĶĢ
    0.09
     anytime
    0.09
    èħ±
    0.09
    Activations Density 0.065%

    No Known Activations