© 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. 17788
    Prev
    Next
    INDEX
    Explanations

    holding events

    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
    主æĮģ
    -0.09
    èµ·åĪ°
    -0.08
     Submission
    -0.08
    åħ³éĶ®æŶåĪ»
    -0.08
    wins
    -0.07
    æĿ¥èĩªäºİ
    -0.07
    Submission
    -0.07
    æĹ¶æ®µ
    -0.07
    PRS
    -0.07
    _CI
    -0.07
    POSITIVE LOGITS
    æĭĽåĭŁ
    0.10
    ç¥ľ
    0.10
    /sources
    0.09
    owns
    0.09
    éħįæĸĻ
    0.09
    è°IJ
    0.09
    è°ĥéħį
    0.09
     ëıĻìĭľ
    0.09
    åı¹æģ¯
    0.09
    æī£
    0.09
    Activations Density 0.061%

    No Known Activations