© 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. 3802
    Prev
    Next
    INDEX
    Explanations

    church events

    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
    éĥ¨åī¯
    -0.09
    çļĦ羣å®ŀ
    -0.08
    羣å®ŀ
    -0.08
    èĨ¦
    -0.08
    cher
    -0.08
    赤
    -0.08
     Bas
    -0.08
    æĮĤ
    -0.08
    omi
    -0.08
    æ¼Ĥ
    -0.08
    POSITIVE LOGITS
    owell
    0.09
    lda
    0.09
    å½±åĵįåĬĽçļĦ
    0.09
     Frontier
    0.09
    è½®
    0.08
    æ´»è·ĥ
    0.08
    _gradients
    0.08
    ç»®
    0.08
     gracefully
    0.08
    éĢĬ
    0.08
    Activations Density 0.048%

    No Known Activations