© 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. 9413
    Prev
    Next
    INDEX
    Explanations

    already been or will be

    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
    _LESS
    -0.09
    æĽ´å®¹æĺĵ
    -0.08
    ont
    -0.08
    ç¼Ĺ
    -0.08
    éĽĨèģļ
    -0.08
    纳ç¨İ
    -0.08
     Chapel
    -0.08
    çĵ·
    -0.08
    æĸĹ
    -0.08
    ToObject
    -0.08
    POSITIVE LOGITS
    ä¹Łä¸įä¾ĭå¤ĸ
    0.10
    .records
    0.10
    ç¿ĺ
    0.09
    æľªçŁ¥
    0.09
    .instructions
    0.09
    (Unknown
    0.09
     coup
    0.09
    ç»ĵæŀľæĺ¾ç¤º
    0.09
    éĤ£ä¸ªäºº
    0.09
    ssp
    0.09
    Activations Density 0.035%

    No Known Activations