© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 53644
    Prev
    Next
    INDEX
    Explanations

    birds, coyotes, species

    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
    æĪIJç«ĭ
    -0.12
    çŁ³åĮĸ
    -0.11
    èĿĩ
    -0.10
    åľ°éģĵ
    -0.10
    æĸĻ
    -0.09
    æ´Ħ
    -0.09
    çݳ
    -0.09
    é¦Ĭ
    -0.09
    ç¢ĩ
    -0.08
    è¥ģ
    -0.08
    POSITIVE LOGITS
    家å±ŀ
    0.09
    æĶĢ
    0.09
    æıIJéĨĴ
    0.09
    æ¢ĵ
    0.09
    åĭ¤å¥ĭ
    0.09
    çŃij
    0.08
    setDefault
    0.08
    tti
    0.08
    æĺ¥èĬĤæľŁéĹ´
    0.08
    å¹»æĥ³
    0.08
    Activations Density 0.089%

    No Known Activations