© 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. 38775
    Prev
    Next
    INDEX
    Explanations

    fridge needs, mom often, stats and

    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
    orem
    -0.14
    ä½Ĩä¸įéĻIJäºİ
    -0.10
    hip
    -0.09
    ss
    -0.09
    ãģĦãĤĭ
    -0.09
    mente
    -0.09
    æ®Ĩ
    -0.09
    à¹Į
    -0.09
    ize
    -0.09
    ump
    -0.09
    POSITIVE LOGITS
    ðŁı»
    0.13
    åĴª
    0.13
    istory
    0.12
    说æĺ¯
    0.12
    ðŁı¼
    0.10
    ðŁı½
    0.09
    lez
    0.09
    urations
    0.09
    isl
    0.09
    imized
    0.09
    Activations Density 0.158%

    No Known Activations