© 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. 50926
    Prev
    Next
    INDEX
    Explanations

    peak or height

    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
    illion
    -0.10
    æĪ¡
    -0.09
    ä¸Ģç»Ħ
    -0.09
    ãģĶ覧
    -0.09
    .jd
    -0.09
    ç©¿è¶Ĭ
    -0.09
    ernals
    -0.08
    ä¹Łä¸įè¦ģ
    -0.08
    ãĥľãĥ¼
    -0.08
    uby
    -0.08
    POSITIVE LOGITS
     peak
    0.13
    å·ħå³°
    0.13
    é«ĺå³°æľŁ
    0.13
    é«ĺå³°
    0.12
     Peak
    0.11
    Peak
    0.11
    æĹ¶æľŁ
    0.10
    çijļ
    0.10
    å¹´è½»
    0.10
    åĪĥ
    0.10
    Activations Density 0.021%

    No Known Activations