© 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. 48717
    Prev
    Next
    INDEX
    Explanations

    last meal she eats

    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
    Moon
    -0.09
    åħģ
    -0.09
    æĩĪ
    -0.09
    伸åĩº
    -0.09
     Moon
    -0.08
    åŀ¢
    -0.08
    èįĴ
    -0.08
     sill
    -0.08
    éĢµ
    -0.08
    еÑĩа
    -0.08
    POSITIVE LOGITS
    被åĬ¨
    0.10
    åĨįä¹Łä¸į
    0.10
    combe
    0.10
    åIJİæĤĶ
    0.09
    ä¹°åįķ
    0.09
    æ»ĭåij³
    0.09
     Walters
    0.09
    失åİ»
    0.09
     unwanted
    0.09
    å°±æĪIJäºĨ
    0.09
    Activations Density 0.100%

    No Known Activations