© 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. 21549
    Prev
    Next
    INDEX
    Explanations

    celebrity names and titles

    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
    pix
    -0.09
    æľįåĬ¡ä½ĵç³»
    -0.09
    认
    -0.09
    åİĤ
    -0.09
    cro
    -0.08
     воÑĤ
    -0.08
    ä¸ľè¥¿
    -0.08
    éĤ£ä»½
    -0.08
     fim
    -0.08
    aldo
    -0.08
    POSITIVE LOGITS
    bio
    0.10
    ieve
    0.10
    è¿Ļå¼ł
    0.09
    æĺĩ
    0.09
    æ©¡
    0.09
    æ´²
    0.09
    bru
    0.09
    ä¸Ģå¼ł
    0.08
    æĻ®éĢļè¯Ŀ
    0.08
    ubb
    0.08
    Activations Density 0.234%

    No Known Activations