© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 29679
    Prev
    Next
    INDEX
    Explanations

    keep

    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
    æĭĴ
    -0.10
    æľīä¸Ģ天
    -0.09
    享
    -0.09
    erno
    -0.09
    lycer
    -0.08
    ä»Ģä¹Īåľ°æĸ¹
    -0.08
    Sink
    -0.08
    roach
    -0.08
    OI
    -0.08
    iously
    -0.08
    POSITIVE LOGITS
    éªħ
    0.09
    è·ª
    0.09
    rawl
    0.09
    ç§
    0.09
    æīĵäºĨ
    0.09
    åIJĬ顶
    0.09
     screenings
    0.09
    ~~~~~~~~~~~~~~~~
    0.09
    代价
    0.08
    姹
    0.08
    Activations Density 0.009%

    No Known Activations