© 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. 61545
    Prev
    Next
    INDEX
    Explanations

    test and exam

    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
    éĻĮ
    -0.09
    èĬĴ
    -0.09
    åªĴ
    -0.08
    åıĹçIJĨ
    -0.08
    èĥĨ
    -0.08
    åĺ´éĩĮ
    -0.08
    ç»Ī身
    -0.08
    åĪ°çİ°åľ¨
    -0.08
    enos
    -0.08
    è²Į
    -0.08
    POSITIVE LOGITS
    åį·
    0.11
     test
    0.10
    ç¿ķ
    0.10
    æľīæľŁ
    0.10
    test
    0.10
    è¯ķåį·
    0.10
    çŃĶåį·
    0.09
     Dough
    0.09
    Pieces
    0.09
    /Test
    0.09
    Activations Density 0.041%

    No Known Activations