© 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. 47416
    Prev
    Next
    INDEX
    Explanations

    an/a variety, number, or quantity

    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
    Negative Logits
    åIJĦä½į
    -0.11
    éĩijéĴ±
    -0.09
    æĢĢ
    -0.08
    oeff
    -0.08
     ÑģебÑı
    -0.08
    LinkId
    -0.08
    设计æĸ¹æ¡Ī
    -0.08
     helf
    -0.08
     Lights
    -0.08
    çĥ«
    -0.08
    POSITIVE LOGITS
     bra
    0.09
    jer
    0.09
    ä¸İåıijå±ķ
    0.09
    iders
    0.09
    第äºĮæī¹
    0.09
    顽
    0.09
    èݽ
    0.09
    _AES
    0.09
    åħ¨éĿ¢åıijå±ķ
    0.09
    isis
    0.08
    Activations Density 0.072%

    No Known Activations