© 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. 19585
    Prev
    Next
    INDEX
    Explanations

    butter or ghee

    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
    åı®
    -0.09
     Vide
    -0.09
    ç»ĻæĤ¨
    -0.09
    åī©ä¸ĭ
    -0.09
    åĹĦ
    -0.09
    èĦ±é¢ĸèĢĮåĩº
    -0.08
    emen
    -0.08
    äºĮæīĭ
    -0.08
     behalf
    -0.08
    _cached
    -0.08
    POSITIVE LOGITS
    ä¹Łåı¯
    0.10
    orgh
    0.09
    æģ©
    0.09
     cgi
    0.08
    çĦ¦
    0.08
     Guerr
    0.08
    åIJĮç±»
    0.08
    ç«Ń
    0.08
    éĴ§
    0.08
    ä»»ä½ķ
    0.08
    Activations Density 0.035%

    No Known Activations