© 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. 32698
    Prev
    Next
    INDEX
    Explanations

    Bell

    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
    elson
    -0.09
    缼å¼Ģ
    -0.08
    eward
    -0.08
    elan
    -0.08
    ksen
    -0.08
    eld
    -0.08
    suming
    -0.08
    agement
    -0.08
    agem
    -0.08
    olley
    -0.08
    POSITIVE LOGITS
    ows
    0.14
    çĿ£ä¿ĥ
    0.10
    isable
    0.09
    è¿Ļä¹Łæĺ¯
    0.09
    xba
    0.09
    arter
    0.09
     дело
    0.09
    ÙĬت
    0.09
    ares
    0.09
    ë§ŀ
    0.09
    Activations Density 0.015%

    No Known Activations