© 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. 19524
    Prev
    Next
    INDEX
    Explanations

    a/an followed by a noun

    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
    aver
    -0.09
    è¿Ļä¹Īåģļ
    -0.08
    建档
    -0.08
    ucher
    -0.08
    odu
    -0.08
    éĻIJé¢Ŀ
    -0.07
    åĪļéľĢ
    -0.07
    è¿ĽæŃ¥
    -0.07
     Friendly
    -0.07
    好好
    -0.07
    POSITIVE LOGITS
    空æ°Ķä¸Ń
    0.10
    èĦijåŃIJéĩĮ
    0.09
    æ¶īåıĬåĪ°
    0.09
    -Feb
    0.09
    çĸ²
    0.09
    åŁºæľ¬ä¸Ĭ
    0.09
    表éĿ¢ä¸Ĭ
    0.09
    лÑĥÑĪ
    0.08
    aised
    0.08
     electorate
    0.08
    Activations Density 0.120%

    No Known Activations