© 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. 29717
    Prev
    Next
    INDEX
    Explanations

    curves and tight body parts

    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
     кÑĢÑĭÑĪ
    -0.10
    å·¦æīĭ
    -0.09
    çIJĨæĢ§
    -0.08
    çĶ¨æ°´
    -0.08
    bane
    -0.08
    æ··ä¹±
    -0.08
    ÐĽÐŀ
    -0.08
    çIJĨ念
    -0.08
    tern
    -0.08
    horn
    -0.08
    POSITIVE LOGITS
    ç¿ĺ
    0.13
    tails
    0.13
    ç¿
    0.10
     jig
    0.10
    èĩĢ
    0.10
    tail
    0.09
    æĴħ
    0.09
     tails
    0.09
    Tail
    0.09
    å¨ĩ
    0.09
    Activations Density 0.048%

    No Known Activations