© 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. 17307
    Prev
    Next
    INDEX
    Explanations

    instructions or calls to action

    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
    enance
    -0.10
    ä½Ĩä»ĸ们
    -0.09
    æѤ类
    -0.09
    æºĺ
    -0.09
    èŁł
    -0.08
    è¡¿
    -0.08
    ç»Ļ大家
    -0.08
    æľ¬æĿ¥
    -0.08
    å«ĸ
    -0.08
    ä½Ĩä»ĸ
    -0.08
    POSITIVE LOGITS
    	IL
    0.09
    çīµ
    0.09
     знаÑĩиÑĤ
    0.09
    ãģªãģıãģªãĤĭ
    0.08
     __________________↵↵
    0.08
    äºĴåĪ©
    0.08
    ãģĬäºĴãģĦ
    0.08
    labs
    0.08
     quo
    0.08
    æĤĿ
    0.08
    Activations Density 0.016%

    No Known Activations