© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 51263
    Prev
    Next
    INDEX
    Explanations

    not understand

    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
    din
    -0.10
    ç®
    -0.10
    éĤĽ
    -0.10
    ç¿Ĭ
    -0.09
     tiên
    -0.09
     expectedResult
    -0.08
    åķ¥
    -0.08
    æĹģ
    -0.08
    å¿ħçĦ¶
    -0.08
     Yao
    -0.08
    POSITIVE LOGITS
    åıijå±ķ
    0.10
    åıijå±ķéĺ¶æ®µ
    0.09
    ç§ijåѦåıijå±ķ
    0.09
    æĺ¯éŁ©åĽ½
    0.08
    å°Ķæĸ¯
    0.08
     çev
    0.08
    anie
    0.08
    ÙħØ«ÙĦ
    0.08
    cope
    0.08
    åģļåĪ°
    0.08
    Activations Density 0.029%

    No Known Activations