© 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. 39539
    Prev
    Next
    INDEX
    Explanations

    screwing up

    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
    åºĶ对
    -0.09
    kul
    -0.09
    ÑĦеÑĢ
    -0.09
    è¾ĥ强
    -0.09
    ê´ij
    -0.09
    人群ä¸Ń
    -0.08
    éĿŀ常åĸľæ¬¢
    -0.08
    æĬµæĬĹ
    -0.08
     noqa
    -0.08
    ç«ĭä½ĵ
    -0.08
    POSITIVE LOGITS
    è¾ľè´Ł
    0.14
    èĢ½è¯¯
    0.14
    æīĵæī°
    0.14
    è´»
    0.14
     jeopard
    0.14
    çİ·
    0.13
    æįŁå®³
    0.12
    éĢłæĪIJ
    0.12
     endanger
    0.12
    åĬłéĩį
    0.12
    Activations Density 0.117%

    No Known Activations