© 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. 53642
    Prev
    Next
    INDEX
    Explanations

    pH levels and biological conditions

    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
    çĭ®åŃIJ
    -0.10
    带ä¸Ĭ
    -0.09
     Aging
    -0.09
    央
    -0.08
    ERVE
    -0.08
    ButtonType
    -0.08
    è¿ĻæĿ¡è·¯
    -0.08
    apolis
    -0.08
    _Field
    -0.08
     Deer
    -0.08
    POSITIVE LOGITS
    èĹ»
    0.11
    饲æĸĻ
    0.10
    饵
    0.09
    æįŀ
    0.09
    ç¹ģæ®ĸ
    0.09
    æ°´è´¨
    0.09
    sembl
    0.09
     aquarium
    0.09
    缸
    0.08
    饲åħ»
    0.08
    Activations Density 0.063%

    No Known Activations