© 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. 55883
    Prev
    Next
    INDEX
    Explanations

    acronyms or abbreviations

    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
    imar
    -0.09
    管çIJĨå±Ģ
    -0.08
    _CSV
    -0.08
    uly
    -0.08
    aze
    -0.08
    bred
    -0.08
    bast
    -0.08
    åĪĨå·¥
    -0.08
    uis
    -0.08
    ç®Ģ称
    -0.08
    POSITIVE LOGITS
     acronym
    0.10
    /OR
    0.09
    usercontent
    0.09
    çIJī
    0.09
    çļĦæĹ¥åŃIJ
    0.09
    æ¸IJ
    0.09
    åĦ¿
    0.09
    entifier
    0.09
    /MM
    0.08
    /MPL
    0.08
    Activations Density 0.983%

    No Known Activations