© 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. 5425
    Prev
    Next
    INDEX
    Explanations

    company abbreviations like CO, INC, or ICO

    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
    ../../../
    -0.11
    æŃ¤åŁºç¡Ģä¸Ĭ
    -0.10
    ãģıãĤĮ
    -0.10
    makers
    -0.09
    оÑģÑĮ
    -0.08
    maker
    -0.08
    ikes
    -0.08
    ken
    -0.08
    crest
    -0.08
    ogeneous
    -0.08
    POSITIVE LOGITS
    elho
    0.10
    çĶŁäº§çļĦ
    0.10
    ço
    0.10
    æĸ«
    0.10
    xon
    0.09
    ptom
    0.09
    俪
    0.09
    Õ®
    0.09
    alesce
    0.09
    ords
    0.09
    Activations Density 0.050%

    No Known Activations