© 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. 32597
    Prev
    Next
    INDEX
    Explanations

    list, retrieve, upload, display, entered

    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
    achel
    -0.09
    INED
    -0.09
    ä¸ĢæľŁ
    -0.09
    weis
    -0.09
    lessly
    -0.09
    /lic
    -0.09
    Interior
    -0.09
    ä¸Ńå¤ĸ
    -0.08
    çIJ¥
    -0.08
    cord
    -0.08
    POSITIVE LOGITS
    -focused
    0.09
    ulação
    0.09
    æ¿ij
    0.09
    åĪ°åºķæĺ¯
    0.08
    åĴĮæľįåĬ¡
    0.08
    ä¸į失
    0.08
    çļĦç¡®æĺ¯
    0.08
    åIJĥå®Į
    0.08
    æݸ
    0.08
    åĤ¬çĶŁ
    0.08
    Activations Density 2.540%

    No Known Activations