© 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. 34729
    Prev
    Next
    INDEX
    Explanations

    awards and categories

    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
    LOPT
    -0.10
    unken
    -0.09
    çļĩ
    -0.09
    å¡ŀå°Ķ
    -0.09
    oader
    -0.09
    ðŁĵ¥
    -0.09
    poke
    -0.09
    aben
    -0.08
    rette
    -0.08
    èĦijè¢ĭ
    -0.08
    POSITIVE LOGITS
     اÙĦÙĪاØŃد
    0.09
    æĸ°æĺ¥
    0.09
    æĺ¥å¤ı
    0.08
    æĻļé¥Ń
    0.08
    å¾ĹæĦı
    0.08
    ãĥĮ
    0.08
    _PRIORITY
    0.08
    ilon
    0.08
    æĸ°äº¬
    0.08
    辫
    0.08
    Activations Density 0.054%

    No Known Activations