© 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. 19382
    Prev
    Next
    INDEX
    Explanations

    Arabic names, places, or script suffixes

    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
    оÑģоб
    -0.09
    dbg
    -0.09
    èĴ¿
    -0.08
    itters
    -0.08
    OUS
    -0.08
    ä¸Ģ群
    -0.08
    æ¢ħèĬ±
    -0.08
    è¿ĻäºĽäºº
    -0.07
    erule
    -0.07
    ::::::
    -0.07
    POSITIVE LOGITS
    çĦ¶å¾Į
    0.10
    ÑĩаÑģ
    0.09
    åīįæıIJæĺ¯
    0.09
    车åºĵ
    0.08
    gar
    0.08
    çĭ¬ä¸Ģ
    0.08
    åĶ§
    0.08
    èŁĨ
    0.08
    plet
    0.08
    çķª
    0.08
    Activations Density 0.143%

    No Known Activations