© 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. 63250
    Prev
    Next
    INDEX
    Explanations

    science fiction inventions and scientists

    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
    ucking
    -0.10
    efs
    -0.09
     khá»ı
    -0.08
    ç»´æĿĥ
    -0.08
    _DISPATCH
    -0.08
    ragon
    -0.08
    黥
    -0.08
    afen
    -0.08
     economics
    -0.08
    ä¸ĭ车
    -0.08
    POSITIVE LOGITS
    å®ŀéªĮ
    0.13
    å®ŀéªĮ室
    0.13
    çłĶ究æĪIJæŀľ
    0.13
    çłĶåĪ¶
    0.13
    è¯ķéªĮ
    0.12
    ç§ijåѦçłĶ究
    0.12
    æĶ¹èī¯
    0.12
     ìĹ°êµ¬
    0.12
    çłĶåıij
    0.12
    çłĶ究
    0.11
    Activations Density 0.057%

    No Known Activations