© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 21199
    Prev
    Next
    INDEX
    Explanations

    give up

    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
    metis
    -0.09
    æĸ°æµªå¾®åįļ
    -0.09
     clos
    -0.09
    åľ¨ä»ĸçļĦ
    -0.08
    æĭ¿çĿĢ
    -0.08
    خار
    -0.08
    _gamma
    -0.08
    丼
    -0.08
    å¯Į
    -0.08
    éģ²
    -0.08
    POSITIVE LOGITS
    è¹Ī
    0.11
    æ®ĥ
    0.10
    åĩ¡äºĭ
    0.09
    éĴī
    0.09
    иÑĤÑģÑı
    0.09
    åij¸
    0.09
    è°±åĨĻ
    0.09
     деÑĤи
    0.08
    åĨķ
    0.08
     Doub
    0.08
    Activations Density 0.019%

    No Known Activations