© 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. 63580
    Prev
    Next
    INDEX
    Explanations

    Randolph County

    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
    éªĪ
    -0.10
    æĬµæĮ¡
    -0.09
    è¿ĽéŨ
    -0.09
    éªł
    -0.09
    åħĥå®Ŀ
    -0.09
     пиÑĤаниÑı
    -0.09
    proto
    -0.09
    çī¹åĪ«æĺ¯åľ¨
    -0.08
    éķ¿å¤§
    -0.08
     retval
    -0.08
    POSITIVE LOGITS
    곡
    0.08
    èªĵ
    0.08
    ald
    0.08
    é£
    0.08
    æĢ¥äºİ
    0.08
    æŁ¥çľĭæĽ´å¤ļ
    0.07
    _reduce
    0.07
    .cloudflare
    0.07
    å¿ĥæĻº
    0.07
    бÑĢа
    0.07
    Activations Density 0.047%

    No Known Activations