© 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. 61722
    Prev
    Next
    INDEX
    Explanations

    VGA camera

    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
    locator
    -0.09
    幸
    -0.09
    reen
    -0.08
    ä¸ĩ象
    -0.08
    uddle
    -0.08
    isl
    -0.08
    affe
    -0.08
    olid
    -0.08
    çŁ³å®¶
    -0.08
    sandbox
    -0.08
    POSITIVE LOGITS
    æĸ°æĹ¶ä»£
    0.09
    eyJ
    0.09
    èĦ¯
    0.09
     sized
    0.09
    -sized
    0.09
    æĸ°æĹ¶æľŁ
    0.08
    ç¼İ
    0.08
    ooter
    0.08
    éĤ¯
    0.08
    çħħ
    0.08
    Activations Density 0.007%

    No Known Activations