© 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. 10312
    Prev
    Next
    INDEX
    Explanations

    originating from

    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
    çīĮ
    -0.08
    满æĢĢ
    -0.08
     Hoover
    -0.08
     ren
    -0.08
    ä¸ŃåĽ½æ¢¦
    -0.08
    çļĦä¸Ģéĥ¨åĪĨ
    -0.08
    9
    -0.08
    isa
    -0.08
    gener
    -0.07
    7
    -0.07
    POSITIVE LOGITS
    åIJĮä¸Ģ
    0.11
    ErrorException
    0.10
    .intent
    0.10
    æķħæĦı
    0.09
     Everett
    0.09
    èĴ¯
    0.09
    .opens
    0.09
    åĵģ
    0.09
     ÑĪиÑĢ
    0.09
    å®ŀæĸ½ç»ĨåĪĻ
    0.09
    Activations Density 0.054%

    No Known Activations