© 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. 48929
    Prev
    Next
    INDEX
    Explanations

    emoticons and special characters

    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
    usk
    -0.09
    çĶŁèĤĸ
    -0.09
    eturn
    -0.08
    åĽ½çİĭ
    -0.08
    ä¸ĭå±ŀ
    -0.08
    æĢ»ç»Ł
    -0.08
    åľĥ
    -0.08
    ..
    -0.08
    éĹ·
    -0.08
     Preconditions
    -0.07
    POSITIVE LOGITS
    .NewRequest
    0.09
    ÑģоÑĢ
    0.09
    atcher
    0.09
     Moff
    0.09
    phin
    0.09
    çļĦåİĭåĬĽ
    0.08
     ÙĪÙģÙĬ
    0.08
    ãĥ¡ãĥª
    0.08
    ertainment
    0.08
     bırak
    0.08
    Activations Density 0.017%

    No Known Activations