© 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. 26114
    Prev
    Next
    INDEX
    Explanations

    resistance, friction, and losses

    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
    èħ¾
    -0.10
    è¹²
    -0.09
    触åıij
    -0.09
    æĬ±åĽ¢
    -0.09
    aval
    -0.09
    æħİéĩį
    -0.09
    ä¸ĢæŶ
    -0.09
    俨
    -0.09
    å¹ķåIJİ
    -0.09
    ingle
    -0.08
    POSITIVE LOGITS
    éĺ»åĬĽ
    0.14
    æij©æĵ¦
    0.10
    æįŁèĢĹ
    0.10
     resistance
    0.10
     Resistance
    0.10
     losses
    0.10
     loss
    0.09
    Resistance
    0.09
    -loss
    0.09
    æįŁå¤±
    0.09
    Activations Density 0.087%

    No Known Activations