© 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. 18616
    Prev
    Next
    INDEX
    Explanations

    temperature descriptions

    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
    weis
    -0.10
    æ®ĭ
    -0.09
    åħµé©¬
    -0.09
    ç®Ĺ
    -0.09
    (home
    -0.09
    Ral
    -0.09
    èķī
    -0.08
    ìĦ
    -0.08
    dsl
    -0.08
    æĻ®éģį
    -0.08
    POSITIVE LOGITS
    aille
    0.10
    æĹ¥åŃIJ
    0.09
    perate
    0.09
    åĮĸ身
    0.08
    atters
    0.08
    ä¸įçĽ¸ä¿¡
    0.08
    å¹´éĻIJ
    0.08
    ä¸įè¦ģ太
    0.08
    é£Ĵ
    0.08
    æľīäºĨ
    0.08
    Activations Density 0.030%

    No Known Activations