© 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. 18178
    Prev
    Next
    INDEX
    Explanations

    said that

    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
    anton
    -0.09
     ups
    -0.09
     MOTOR
    -0.08
    æ±īæĹı
    -0.08
    _MR
    -0.08
    åĨ¬åŃ£
    -0.08
    æĮij
    -0.08
    åĶĨ
    -0.08
    ä¸ľè·¯
    -0.08
    æ·±å¤Ħ
    -0.08
    POSITIVE LOGITS
    å±ģèĤ¡
    0.10
    æľī两ç§į
    0.10
    æľĢ好çļĦ
    0.10
    æĢĢéĩĮ
    0.10
    çģµéŃĤ
    0.10
    好çľĭçļĦ
    0.09
    äºĶåĪĨéĴŁ
    0.09
    åĶ¯ä¸ĢçļĦ
    0.09
    æīĺ
    0.08
    åĶ¯ä¸Ģ
    0.08
    Activations Density 0.115%

    No Known Activations