© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 52538
    Prev
    Next
    INDEX
    Explanations

    formula for luck

    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
    è¯īæ±Ĥ
    -0.10
    /cms
    -0.09
    ä»·ä½į
    -0.09
    åįģä¹Ŀ大
    -0.08
    ITU
    -0.08
     hoped
    -0.08
    аÑĢÑĤ
    -0.08
     اÙĦخبر
    -0.08
     Bru
    -0.08
    é«ĺä½İ
    -0.08
    POSITIVE LOGITS
    mez
    0.10
    躬
    0.10
    èĬĴ
    0.10
    ç½ķ
    0.10
    å·´èı²çī¹
    0.10
     Mun
    0.10
    人çĶŁçļĦ
    0.09
    æĩĴ
    0.09
     Naked
    0.09
    人çĶŁ
    0.08
    Activations Density 0.208%

    No Known Activations