© 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. 33810
    Prev
    Next
    INDEX
    Explanations

    dimensions, sizes, or scaling

    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
    æĽ·
    -0.11
    ç°ª
    -0.09
    åĴĢ
    -0.09
    严éĩįå½±åĵį
    -0.09
     ÑĢож
    -0.08
    è¿ĻæĶ¯
    -0.08
    åıŁ
    -0.08
    ç¨ļ
    -0.08
    æ·±åĪ»
    -0.08
    鬼
    -0.08
    POSITIVE LOGITS
    å¹ħ
    0.13
    ä¸¤å¼ł
    0.11
    ä¸Ģå¹ħ
    0.11
    ä¸Ģå¼ł
    0.11
    fern
    0.10
    panse
    0.10
    rans
    0.10
    æĥĬ人
    0.09
    大åŀĭ
    0.09
    æĭ¼
    0.09
    Activations Density 0.183%

    No Known Activations