© 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. 59356
    Prev
    Next
    INDEX
    Explanations

    factorization

    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
    laces
    -0.10
    /false
    -0.10
    ening
    -0.09
    ë¡Ŀ
    -0.09
    isser
    -0.08
    erness
    -0.08
    常说
    -0.08
    ÑģÑĤÑĢа
    -0.08
    оз
    -0.08
    ya
    -0.08
    POSITIVE LOGITS
    ial
    0.16
    ials
    0.15
    ially
    0.14
    cade
    0.13
    nement
    0.11
    à¹Į
    0.11
    ulary
    0.11
    ization
    0.11
    ìĭŃ
    0.10
    ized
    0.10
    Activations Density 0.078%

    No Known Activations