© 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. 54280
    Prev
    Next
    INDEX
    Explanations

    those that who

    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
    èĶĵ
    -0.09
    ialized
    -0.09
    åıĭ好
    -0.09
    ç«ł
    -0.08
    å¾Īåĸľæ¬¢
    -0.08
     Hawth
    -0.08
    visor
    -0.08
    纵
    -0.08
    oli
    -0.08
    çļĦè·¯ä¸Ĭ
    -0.08
    POSITIVE LOGITS
    ITT
    0.10
    ä¹ĭæīĢ
    0.09
     who
    0.09
     اÙĦØ°ÙĬÙĨ
    0.09
    itt
    0.09
    ë¶ķ
    0.09
     кÑĤо
    0.09
    è°ģ
    0.09
    soever
    0.08
     yang
    0.08
    Activations Density 0.070%

    No Known Activations