© 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. 1095
    Prev
    Next
    INDEX
    Explanations

    vehicle categories and licenses

    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
    _mk
    -0.09
    æĿ¥åĽŀ
    -0.09
    itemap
    -0.09
    edd
    -0.09
    ä¸įåIJĪ
    -0.09
    ä¸Ńè¶ħ
    -0.08
    race
    -0.08
    åĪĨå¸ĥåľ¨
    -0.08
    èįĴ
    -0.08
    è¦ģçŁ¥éģĵ
    -0.08
    POSITIVE LOGITS
    驾çħ§
    0.11
    å¹´é¾Ħ段
    0.10
    éĻĦå±ŀ
    0.10
    å¥İ
    0.09
    tol
    0.09
    許
    0.09
    èĭ«
    0.09
    EQ
    0.09
     EQ
    0.09
    æ³£
    0.09
    Activations Density 0.060%

    No Known Activations