© 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. 56276
    Prev
    Next
    INDEX
    Explanations

    correct

    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
    bling
    -0.10
    è¡ħ
    -0.10
    æĵĢ
    -0.10
    ä¸Ģçŀ¬éĹ´
    -0.09
    iture
    -0.09
    cape
    -0.09
    hear
    -0.09
    oh
    -0.09
    ctest
    -0.09
    å¹Ħ
    -0.09
    POSITIVE LOGITS
    çºłæŃ£
    0.13
    ми
    0.11
    è¿ĩæĿ¥
    0.11
    åĴĮå®ĮåĸĦ
    0.10
    人å±ħçݯå¢ĥ
    0.10
    äºĨè¿ĩæĿ¥
    0.09
    nel
    0.09
    éģİä¾Ĩ
    0.09
    åıijçİ°èĩªå·±
    0.09
    çºł
    0.09
    Activations Density 0.028%

    No Known Activations