© 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. 53538
    Prev
    Next
    INDEX
    Explanations

    great-grand

    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
    .tp
    -0.11
    redni
    -0.10
    å¹Į
    -0.10
    å°ıä¼Ļä¼´
    -0.09
    edBy
    -0.09
    uat
    -0.09
    å¹³çŃī
    -0.09
    æİ£
    -0.08
    åĪģ
    -0.08
    åŃĿ
    -0.08
    POSITIVE LOGITS
    rics
    0.09
     Simmons
    0.08
    hip
    0.08
     Klein
    0.08
    DS
    0.08
    们
    0.07
    _rev
    0.07
    èIJ¥
    0.07
    este
    0.07
    pir
    0.07
    Activations Density 0.011%

    No Known Activations