© 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. 47745
    Prev
    Next
    INDEX
    Explanations

    reclining furniture

    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
    éľŃ
    -0.09
    pawn
    -0.08
    itive
    -0.08
    å¼ĢçĿĢ
    -0.08
    ignet
    -0.08
    ahir
    -0.08
    æį§
    -0.08
    ima
    -0.08
    unte
    -0.08
    tal
    -0.08
    POSITIVE LOGITS
    bek
    0.10
    åıĹçIJĨ
    0.10
    ä¸įçĽ¸ä¿¡
    0.10
    elog
    0.09
    oving
    0.09
    ãĥĪãĥ©
    0.09
    ï¸ı
    0.09
    amax
    0.09
    ury
    0.09
    abar
    0.08
    Activations Density 0.007%

    No Known Activations