© 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. 2284
    Prev
    Next
    INDEX
    Explanations

    imgur links or URLs

    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
    еÐ
    -0.10
    éĻĩ
    -0.09
    å½¼
    -0.09
    åıijå±ķ缮æłĩ
    -0.09
    stor
    -0.09
    èıŁ
    -0.08
    带ä¸Ĭ
    -0.08
    åħļåĨħ
    -0.08
     YYSTYPE
    -0.08
    ullet
    -0.08
    POSITIVE LOGITS
    rin
    0.09
    éĤ¯éĥ¸
    0.09
    æŃª
    0.08
    çĿĢå®ŀ
    0.08
    zend
    0.08
    æľ¬æĬ¥
    0.08
    ts
    0.08
    ç½ķ
    0.08
    ipop
    0.08
    èĨĺ
    0.08
    Activations Density 0.001%

    No Known Activations