© 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. 36361
    Prev
    Next
    INDEX
    Explanations

    excessive growth or bodily change

    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
    æĪĺæĸĹ
    -0.09
    _mt
    -0.09
    Slf
    -0.08
    çĹħæ¯ĴæĦŁæŁĵ
    -0.08
    ä¸įåľ¨
    -0.08
    éĢĴ
    -0.08
    ç¥ĵ
    -0.08
     disappoint
    -0.08
    åĶ¤
    -0.08
    ãĥŀãĥ«
    -0.08
    POSITIVE LOGITS
    è¿ĩåī©
    0.20
     excess
    0.15
    è¿ĩ度
    0.15
    åĨĹ
    0.15
    è¿ĩå¤ļ
    0.14
    è¿ĩåĪĨ
    0.14
    è¶ħé¢Ŀ
    0.14
    以èĩ³äºİ
    0.14
    è¶ħåĩº
    0.14
    å¤ļä½Ļ
    0.13
    Activations Density 0.223%

    No Known Activations