© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 1861
    Prev
    Next
    INDEX
    Explanations

    Superintendent (of institutions/schools)

    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
    èĮµ
    -0.09
    æ®Ĩ
    -0.09
    aters
    -0.09
    宥
    -0.09
    çĸ«
    -0.08
    åĦ¿
    -0.08
    ãģ¤ãģį
    -0.08
    çŃĿ
    -0.08
    èĵij
    -0.08
    ight
    -0.08
    POSITIVE LOGITS
    tle
    0.11
    sWith
    0.11
    æŁ¥æĺİ
    0.10
    cies
    0.09
    è¿IJåĬ¨ä¼ļ
    0.09
    IOR
    0.09
    ees
    0.09
    grass
    0.09
    .dex
    0.09
    stood
    0.09
    Activations Density 0.006%

    No Known Activations