© 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. 53606
    Prev
    Next
    INDEX
    Explanations

    to begin with

    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
    èįī
    -0.09
    abad
    -0.09
    indrome
    -0.09
    åıĭåĸĦ
    -0.08
     Bord
    -0.08
    ervo
    -0.08
     ÑģÑĤанеÑĤ
    -0.08
    ä¸įå®Į
    -0.08
    ãģĤãģŁãĤĬ
    -0.08
    çµ®
    -0.08
    POSITIVE LOGITS
    æĪijåıªæĺ¯
    0.11
    æĪijåİ»
    0.09
    æīĵéĢļ
    0.09
    欢è¿İ大家
    0.09
    èĭķ
    0.09
    нÑĮ
    0.09
    çŁŃ线
    0.09
    anny
    0.08
    ä¸ĵä¸ļåĮĸ
    0.08
    å¥ĩå¦Ļ
    0.08
    Activations Density 0.019%

    No Known Activations