© 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. 33796
    Prev
    Next
    INDEX
    Explanations

    cookie / cookies

    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®Ĭ
    -0.11
    çĸ£
    -0.11
    éĽĦåİļ
    -0.10
    æ¹
    -0.10
    èıľ
    -0.10
     Salad
    -0.10
    ç©´
    -0.09
     salad
    -0.09
    ä¸Ģ头
    -0.09
    Selectors
    -0.09
    POSITIVE LOGITS
    饼干
    0.15
     cookies
    0.15
    cookie
    0.15
     cookie
    0.14
    Cookie
    0.13
     Cookies
    0.13
    _cookie
    0.12
    cookies
    0.12
    ðŁįª
    0.12
     Cookie
    0.12
    Activations Density 0.096%

    No Known Activations