© 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. 47484
    Prev
    Next
    INDEX
    Explanations

    I or you speaking

    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
    æī£
    -0.08
    å¤§åĽ½
    -0.08
    产åĵģè´¨éĩı
    -0.08
    бан
    -0.08
     ÑĢаÑģположен
    -0.08
    addPreferredGap
    -0.08
    继
    -0.08
    uala
    -0.08
    æĥ³åĪ°
    -0.08
    åĴĮå¹³
    -0.07
    POSITIVE LOGITS
     же
    0.13
    à¹Ģà¸Ńà¸ĩ
    0.12
    ä¿©
    0.11
    å¿Ŀ
    0.11
    -même
    0.10
    å²
    0.10
     own
    0.10
    è¾Ī
    0.10
    riad
    0.10
     alone
    0.09
    Activations Density 0.172%

    No Known Activations