© 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. 23640
    Prev
    Next
    INDEX
    Explanations

    slightest idea

    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
     Lah
    -0.10
    heel
    -0.10
    è¯ł
    -0.09
    æľĢ大éĻIJ度
    -0.09
    å·²ä¹ħçļĦ
    -0.09
    çİ®
    -0.09
    urlencode
    -0.09
    æ¸IJ
    -0.09
    олж
    -0.08
    quine
    -0.08
    POSITIVE LOGITS
     slightest
    0.11
    ä¹Łä¸įçŁ¥éģĵ
    0.10
    ä¸ĩä¸Ģ
    0.10
    éĽĢ
    0.08
     überhaupt
    0.08
    足以
    0.08
    tweet
    0.08
    icio
    0.08
    è¢Ħ
    0.08
     IData
    0.08
    Activations Density 0.086%

    No Known Activations