© 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. 55405
    Prev
    Next
    INDEX
    Explanations

    university and academic roles

    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
    大ä¸ĵ
    -0.13
    ä¸ĵç§ij
    -0.12
    æĬ±åĽ¢
    -0.11
    èĻļ空
    -0.10
    è½
    -0.10
    绥
    -0.09
    该åİ¿
    -0.09
    åłĨ积
    -0.09
    å±Ģ
    -0.09
    idis
    -0.09
    POSITIVE LOGITS
    /MIT
    0.11
    ãĤ·ãĥª
    0.11
     MIT
    0.10
    åĵĪä½Ľ
    0.10
     Yale
    0.10
    MIT
    0.10
     Stanford
    0.10
    NY
    0.09
    .mit
    0.09
    icago
    0.09
    Activations Density 0.169%

    No Known Activations