© 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. 60874
    Prev
    Next
    INDEX
    Explanations

    Advanced hand sanitizer

    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
    andi
    -0.09
    åħ±é¸£
    -0.09
    ikan
    -0.08
     Mellon
    -0.08
    aman
    -0.08
    åIJĮåŁİ
    -0.08
     hobby
    -0.08
    PIP
    -0.08
    æľīä¸Ģå®ļçļĦ
    -0.08
    anel
    -0.08
    POSITIVE LOGITS
    æ¶īå«Į
    0.09
    oust
    0.09
    Dims
    0.08
    ä¸Ģç±»
    0.08
    tet
    0.08
    æĪIJè¯Ń
    0.08
    åĬłæ²¹ç«Ļ
    0.08
    etten
    0.08
    类产åĵģ
    0.08
    ennis
    0.08
    Activations Density 0.036%

    No Known Activations