© 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. 21876
    Prev
    Next
    INDEX
    Explanations

    put down or return items

    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
    æĭŁå®ļ
    -0.11
    ivals
    -0.09
    ibus
    -0.09
    èį·
    -0.09
    éħ¬
    -0.09
    Cour
    -0.09
    交éĢļæŀ¢çº½
    -0.08
    éĴĿ
    -0.08
    èĦijåŃIJ
    -0.08
    æŀ¢çº½
    -0.08
    POSITIVE LOGITS
    æĶ¾ä¸ĭ
    0.12
    æIJģ
    0.11
    è¾¾æłĩ
    0.10
    éĢĢè¿ĺ
    0.09
     Keystone
    0.09
    .mu
    0.08
    èĦļ
    0.08
     ÑģÑĤало
    0.08
    è¿Ļå¥Ĺ
    0.08
    çģ«çĤ¬
    0.08
    Activations Density 0.039%

    No Known Activations