© 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. 54364
    Prev
    Next
    INDEX
    Explanations

    unpredictable variability

    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
    符
    -0.09
    BIG
    -0.09
     settled
    -0.09
    ä¸İä¼Ĺä¸įåIJĮ
    -0.09
    iminal
    -0.08
    æ¢ĵ
    -0.08
    åºĶ该
    -0.08
    bre
    -0.08
    çī¹æ®ĬçļĦ
    -0.08
    .defaultProps
    -0.08
    POSITIVE LOGITS
    åıĸåĨ³äºİ
    0.14
    è¿IJæ°Ķ
    0.13
    ä¸į稳å®ļ
    0.12
     завиÑģиÑĤ
    0.12
    çļĦåij½è¿IJ
    0.12
    åıĸåĨ³
    0.11
    æ³¢åĬ¨
    0.11
    esti
    0.11
    ðŁİ²
    0.11
    Luck
    0.11
    Activations Density 0.110%

    No Known Activations