© 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. 47845
    Prev
    Next
    INDEX
    Explanations

    versions of games and media

    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
    ÙĨÙĪ
    -0.09
    æ°ijå¿ĥ
    -0.09
     обÑĬ
    -0.08
    æľĽçĿĢ
    -0.08
    pert
    -0.08
    çŁį
    -0.08
    è¿Ļå¼ł
    -0.08
    å§Ĩ
    -0.08
    yc
    -0.08
    ä¸Ģç»Ħ
    -0.08
    POSITIVE LOGITS
    çīĪæľ¬
    0.11
     thereof
    0.11
     versions
    0.11
     version
    0.10
     ваÑĢианÑĤ
    0.10
    ä¸ŃåŃĺåľ¨çļĦ
    0.09
    	version
    0.09
    мол
    0.09
    æĭľ
    0.09
    aversal
    0.08
    Activations Density 0.209%

    No Known Activations