© 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. 39240
    Prev
    Next
    INDEX
    Explanations

    result in

    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
    pics
    -0.09
    latex
    -0.09
    æĢĿæĥ³æĶ¿æ²»
    -0.09
    ãĥ¬ãĤ¹
    -0.09
    ãĥ¼ãĤº
    -0.09
    åĦ¿
    -0.08
    èĬĤå¥ı
    -0.08
    åĺīå¹´åįİ
    -0.08
    ç«ĭå¿Ĺ
    -0.08
    riad
    -0.08
    POSITIVE LOGITS
    äºİä¸Ģä½ĵ
    0.12
    åľ¨æľªæĿ¥
    0.10
    ult
    0.10
    éĶ´
    0.09
    äºİ
    0.09
    öne
    0.09
    exas
    0.08
    uate
    0.08
    sockopt
    0.08
    /render
    0.08
    Activations Density 0.030%

    No Known Activations