© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 62503
    Prev
    Next
    INDEX
    Explanations

    green growth

    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
    éĿŀ常åĸľæ¬¢
    -0.09
    èµı
    -0.09
    atas
    -0.09
    å½ĵ代
    -0.09
    éĥ½éĿŀ常
    -0.09
    cone
    -0.09
    çĢijå¸ĥ
    -0.09
    å«ĸ
    -0.08
     Bios
    -0.08
    å«¡
    -0.08
    POSITIVE LOGITS
    çĤ¹æ»´
    0.10
    amespace
    0.09
    è¿ĺæĺ¯
    0.09
    æĽ´è¦ģ
    0.09
    缩水
    0.08
    è¿ĺæĺ¯è¦ģ
    0.08
     versus
    0.08
    ?:
    0.08
    Äĭ
    0.08
    istogram
    0.08
    Activations Density 0.487%

    No Known Activations