© 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. 12412
    Prev
    Next
    INDEX
    Explanations

    Faired bike, motorcycle, sport

    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
    entially
    -0.11
    è°Ķ
    -0.10
    naires
    -0.10
    èIJ©
    -0.10
    æĸ°çļĦ
    -0.09
    èĭ´
    -0.09
    éĤ£æŶåĢĻ
    -0.09
    zens
    -0.09
    Unused
    -0.09
    opus
    -0.08
    POSITIVE LOGITS
    æŃ¤åŁºç¡Ģä¸Ĭ
    0.10
    an
    0.09
    åIJĦæł·
    0.09
    0
    0.09
    åĵº
    0.09
    b
    0.08
    æį
    0.08
    u
    0.08
    ent
    0.08
    own
    0.08
    Activations Density 0.404%

    No Known Activations