© 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. 54125
    Prev
    Next
    INDEX
    Explanations

    celebrity news and updates

    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
    人æ°ij群ä¼Ĺ
    -0.09
    订
    -0.09
    龸çİĭ
    -0.09
    nuts
    -0.09
     foss
    -0.09
    è¸ŀ
    -0.08
    pec
    -0.08
    맼
    -0.08
    éĿŀçī©è´¨
    -0.08
    åIJį为
    -0.08
    POSITIVE LOGITS
    åĴĮæĬĢæľ¯
    0.10
    è´º
    0.09
    éŀł
    0.09
    æķ¬
    0.09
    [sub
    0.09
    æķ
    0.08
    metic
    0.08
    воÑĢ
    0.08
     backing
    0.08
    urma
    0.08
    Activations Density 0.011%

    No Known Activations