© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 8822
    Prev
    Next
    INDEX
    Explanations

    right side phrases

    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
    æ±
    -0.09
    çļĦä¸Ģéĥ¨åĪĨ
    -0.09
    ä¸įåľ¨ä¹İ
    -0.09
    ukes
    -0.08
    éĻ¢éĻ¢éķ¿
    -0.08
    ettes
    -0.08
    ivos
    -0.08
    ç¿¡ç¿ł
    -0.08
    etine
    -0.08
    ÙĪÙħØ©
    -0.08
    POSITIVE LOGITS
    ered
    0.10
    çĽ¥
    0.09
    éĢıè§Ĩ
    0.08
    бав
    0.08
    è¿ĺåİŁ
    0.08
    ewan
    0.08
    触åıĬ
    0.08
    ERING
    0.07
    expect
    0.07
     sanctions
    0.07
    Activations Density 0.002%

    No Known Activations