© 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. 53296
    Prev
    Next
    INDEX
    Explanations

    speed up or slow down

    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
    俳
    -0.12
    è¿Ļæł·ä¸ĢæĿ¥
    -0.11
    çĪ·
    -0.10
    代åŃķ
    -0.10
    ä½ľèĢħæīĢæľī
    -0.10
    管çIJĨæĿ¡ä¾ĭ
    -0.09
    æ¶İ
    -0.09
    egr
    -0.09
    ookies
    -0.09
    æĻļæĬ¥
    -0.09
    POSITIVE LOGITS
    gee
    0.10
    èĦļæŃ¥
    0.09
    orm
    0.08
    踽
    0.08
    çĶ»éĿ¢
    0.08
    -turned
    0.08
    宪
    0.07
    åľºéĿ¢
    0.07
    身åŃIJ
    0.07
    hub
    0.07
    Activations Density 0.008%

    No Known Activations