© 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. 2331
    Prev
    Next
    INDEX
    Explanations

    on-air, screen, stage, field

    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
    ç½ijä¸Ĭ
    -0.11
    çªĿ
    -0.10
    iest
    -0.10
    åľ¨ç½ijä¸Ĭ
    -0.10
    ustr
    -0.09
    fare
    -0.09
    天é¹ħ
    -0.09
    åľ¨åIJĮä¸Ģ
    -0.09
    ounds
    -0.09
    æĥij
    -0.09
    POSITIVE LOGITS
    /off
    0.13
     behalf
    0.12
    çĽĸ
    0.09
     ÑħÑĢ
    0.09
    jective
    0.09
    çĺ¾
    0.09
    èĵĭ
    0.09
    èģ²æĺİ
    0.08
     SÆ¡n
    0.08
    è¡®
    0.08
    Activations Density 0.012%

    No Known Activations