© 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. 38679
    Prev
    Next
    INDEX
    Explanations

    Trudeau vacation album strike

    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
    alog
    -0.10
    æĺ¯æ¯Ķè¾ĥ
    -0.09
    èĭŀ
    -0.09
    ness
    -0.09
     gì
    -0.09
    çªģå¦Ĥåħ¶
    -0.09
    eras
    -0.09
    esh
    -0.08
    ัà¸ģ
    -0.08
    æŁŀ
    -0.08
    POSITIVE LOGITS
    on
    0.11
    reas
    0.10
    rez
    0.10
    çļĦæĹ¥åŃIJéĩĮ
    0.10
    ses
    0.09
    utely
    0.09
    /OR
    0.09
    orp
    0.09
    pike
    0.09
    itic
    0.09
    Activations Density 0.018%

    No Known Activations