© 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. 17900
    Prev
    Next
    INDEX
    Explanations

    scholarships and fellows

    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
    ete
    -0.10
    åıªæľīä¸Ģ个
    -0.09
    _exports
    -0.09
    èµ·æĿ¥äºĨ
    -0.09
    Kn
    -0.09
    aris
    -0.08
    å¤ĸç±į
    -0.08
    åIJĮè¡Į
    -0.08
    æķĿ
    -0.08
    reme
    -0.08
    POSITIVE LOGITS
    å¼Ģåı£
    0.09
     ford
    0.09
     opening
    0.08
    idy
    0.08
     Abyss
    0.08
    ãģ¡
    0.08
    åĪļ
    0.08
    éĹ´
    0.08
    æľĿéĺ³
    0.08
    åŁł
    0.08
    Activations Density 0.008%

    No Known Activations