© 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. 56222
    Prev
    Next
    INDEX
    Explanations

    drivers, teams, partners

    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
    _IMPLEMENT
    -0.10
    ä½İ头
    -0.10
    åĪijäºĭæ¡Ī件
    -0.09
    æ¾ī
    -0.09
    lopen
    -0.09
    æķŀå¼Ģ
    -0.09
    cÃŃ
    -0.09
    羣缸
    -0.09
    ä¸įå¦Ĥ
    -0.08
    ä¹ĸä¹ĸ
    -0.08
    POSITIVE LOGITS
    å¤ĩæĪĺ
    0.09
    éĤ¬
    0.09
    åĽ¢éķ¿
    0.09
    åħļåĴĮåĽ½å®¶
    0.09
     adv
    0.09
    åĬ¡å¿ħ
    0.09
     Morr
    0.09
    å¨ģå°Ķ
    0.08
    åݲ
    0.08
     GANG
    0.08
    Activations Density 0.070%

    No Known Activations