© 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. 38641
    Prev
    Next
    INDEX
    Explanations

    glia, stromal cells, retinitis

    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
    æij©
    -0.09
    horn
    -0.09
    ç»ĵ
    -0.09
    æİ·
    -0.08
    poster
    -0.08
    charm
    -0.08
    äºİ
    -0.08
    (Return
    -0.08
    rape
    -0.08
    æ¯Ĺ
    -0.08
    POSITIVE LOGITS
     enjo
    0.11
    WISE
    0.09
    ä»İåīį
    0.09
    è¯ł
    0.09
    蹩
    0.09
    æĸŁ
    0.09
    æŁģ
    0.09
    æ£ł
    0.09
    æĬ½
    0.09
    éĴ¿
    0.08
    Activations Density 0.196%

    No Known Activations