© 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. 6391
    Prev
    Next
    INDEX
    Explanations

    table and desktop surfaces

    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
    ç©¿
    -0.10
    ARRY
    -0.10
    arry
    -0.09
     Gallagher
    -0.09
     adına
    -0.09
     slur
    -0.09
    å¼ķè¿Ľ
    -0.09
    åĢĻ
    -0.09
    太平æ´ĭ
    -0.08
    èĶŁ
    -0.08
    POSITIVE LOGITS
    æ¡Įä¸Ĭ
    0.20
    æ¡ĮåŃIJä¸Ĭ
    0.18
    æ¡Į
    0.18
    æ¡ĮéĿ¢
    0.17
     table
    0.13
    desk
    0.13
    åı°
    0.12
    é¤IJæ¡Į
    0.12
    æ¡ĮåŃIJ
    0.11
     desk
    0.11
    Activations Density 0.071%

    No Known Activations