© 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. 9847
    Prev
    Next
    INDEX
    Explanations

    Cisco, attributes, electron, library

    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
    æĥĬ人
    -0.11
    è¾ĵéĢģ
    -0.09
    é«ĺåħ´
    -0.08
    èįł
    -0.08
    æīįæľī
    -0.08
    ä¼łéĹ»
    -0.08
    æĽĻ
    -0.08
    èµĸ
    -0.08
    é¦ĭ
    -0.08
    è¸Į
    -0.08
    POSITIVE LOGITS
    è¿Ļ两天
    0.09
    alars
    0.09
    æŶéĹ´æ®µ
    0.09
    çŁ¢
    0.09
    çŀ»
    0.09
    uster
    0.09
    åĨ¢
    0.09
    æĸ½
    0.09
    æĹ¶æ®µ
    0.08
    ará
    0.08
    Activations Density 0.006%

    No Known Activations