© 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. 48082
    Prev
    Next
    INDEX
    Explanations

    body parts and actions

    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
    æĪ´
    -0.11
    æĨĭ
    -0.09
    åĩºéŨ
    -0.09
    ä¸ªå·¥ä½ľ
    -0.09
    èļĮ
    -0.09
    æ±²
    -0.09
    è´»
    -0.09
    è´§
    -0.09
     Tubes
    -0.09
    æĤ¼
    -0.09
    POSITIVE LOGITS
    æij¸
    0.11
    æĬļæij¸
    0.10
    è½®å»ĵ
    0.10
    æį»
    0.10
    è´¨åľ°
    0.09
    è¾ĩ
    0.09
    触æij¸
    0.09
    çĹķ
    0.08
    æİ¢
    0.08
    æľªå©ļ
    0.08
    Activations Density 0.035%

    No Known Activations