© 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. 52700
    Prev
    Next
    INDEX
    Explanations

    results: Breed | Name

    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
    çīĴ
    -0.10
    ãĤ¯ãĥŃ
    -0.09
    é¨İ
    -0.09
    å¸ĸ
    -0.09
    æĮīè§Ħå®ļ
    -0.09
     пÑĢид
    -0.09
    éªij
    -0.08
    quel
    -0.08
    æ¯Ķè¾ĥç®Ģåįķ
    -0.08
    æį®
    -0.08
    POSITIVE LOGITS
    åIJł
    0.10
    èIJĿåįľ
    0.09
    รà¸ĵ
    0.09
    ستاÙĨ
    0.09
    åĨĽåĽ¢
    0.09
    Owners
    0.08
    åħ¥èĤ¡
    0.08
     ÑĤÑĥ
    0.08
    ç«¥è¯Ŀ
    0.08
    TAIL
    0.08
    Activations Density 0.018%

    No Known Activations