© 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. 9192
    Prev
    Next
    INDEX
    Explanations

    newsletter or inbox updates

    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
    缬
    -0.11
    å¸ģ
    -0.10
    éĻį临
    -0.10
    æīĭèĦļ
    -0.09
    åĬĽè¿ĺæĺ¯
    -0.09
    _SI
    -0.09
    æķĻçłĶ
    -0.09
    交æĺĵæīĢ
    -0.09
    å½ĴæĿ¥
    -0.09
    羸
    -0.09
    POSITIVE LOGITS
    .TODO
    0.09
     pret
    0.09
    ä¸ĢæĬĬ
    0.09
    é«ĺåĩº
    0.08
    åªĴ
    0.08
    çŀ½
    0.08
    ombs
    0.08
    æĺł
    0.08
    岫
    0.07
     Zum
    0.07
    Activations Density 0.024%

    No Known Activations