© 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. 53507
    Prev
    Next
    INDEX
    Explanations

    chance

    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
    æħİ
    -0.09
    åIJİçļĦ
    -0.08
     каж
    -0.08
    çĤĻ
    -0.08
    ait
    -0.08
    osite
    -0.08
    istle
    -0.07
     Vin
    -0.07
    èıŁ
    -0.07
    inder
    -0.07
    POSITIVE LOGITS
     chance
    0.22
    Chance
    0.19
     chances
    0.18
     Chance
    0.18
    _chance
    0.16
    æ¦Ĥçİĩ
    0.16
    åĩłçİĩ
    0.16
    æľºä¼ļ
    0.14
     likelihood
    0.13
    çļĦåı¯èĥ½æĢ§
    0.13
    Activations Density 0.064%

    No Known Activations