© 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. 63767
    Prev
    Next
    INDEX
    Explanations

    municipal corporation

    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
    è¹ij
    -0.09
    å³Ļ
    -0.09
    /we
    -0.09
    è¸ŀ
    -0.09
    oute
    -0.08
    lessness
    -0.08
    æĻ¯åĮº
    -0.08
    fully
    -0.08
    èķī
    -0.08
    ä¸Ģç¯ĩæĸĩç«ł
    -0.08
    POSITIVE LOGITS
    ities
    0.14
    ité
    0.11
    ãĥ¡ãĥ³ãĥĪ
    0.10
    ion
    0.10
    ization
    0.10
    stration
    0.09
    strate
    0.09
    oste
    0.09
    ally
    0.09
    aders
    0.09
    Activations Density 0.010%

    No Known Activations