© 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. 11964
    Prev
    Next
    INDEX
    Explanations

    Fiscal Cliff Deal, Mensalão scandal, nuclear option

    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
    æ¹ĸåĮº
    -0.10
    åĺĺ
    -0.10
    inka
    -0.09
    cheme
    -0.09
    akens
    -0.08
    lam
    -0.08
    lis
    -0.08
     валÑİÑĤ
    -0.08
    ç®į
    -0.08
     Symbols
    -0.08
    POSITIVE LOGITS
    çļĦåĪ°æĿ¥
    0.09
    æİīèIJ½
    0.09
    ãĤĴè¿İ
    0.08
    äºĨä¸Ģæī¹
    0.08
    å¿ĥåĬ¨
    0.08
    scr
    0.08
    iesta
    0.08
    æİī
    0.08
    ve
    0.08
    åģľä¸ĭæĿ¥
    0.08
    Activations Density 0.001%

    No Known Activations