© 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. 1385
    Prev
    Next
    INDEX
    Explanations

    reporting speech attribution

    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
    èĪħ
    -0.09
    çĪ¸
    -0.08
    红éħĴ
    -0.08
    éĴ¦
    -0.08
    çĤ¯
    -0.08
     annon
    -0.08
     airports
    -0.08
    ç½ij游
    -0.08
    -sama
    -0.08
    贵宾
    -0.08
    POSITIVE LOGITS
    éĩĩ访
    0.10
    è®°èĢħéĩĩ访
    0.09
    åIJijè®°èĢħ
    0.09
    æİ¥å¾ħ
    0.08
    æĬĬèĩªå·±
    0.08
    ä½ĵéªĮ
    0.08
    ÙĪاء
    0.08
    Registr
    0.08
    itty
    0.08
    çľĭæ³ķ
    0.08
    Activations Density 0.025%

    No Known Activations