© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 52294
    Prev
    Next
    INDEX
    Explanations

    code, app, system, technical programming

    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
    躬
    -0.08
    ued
    -0.08
     hype
    -0.08
    廪
    -0.08
    å¤Ļ
    -0.08
    ä½łçľĭ
    -0.08
    åģıåģı
    -0.08
    wap
    -0.07
    请èģĶç³»
    -0.07
    çĹĪ
    -0.07
    POSITIVE LOGITS
    æķĸ
    0.10
    marsh
    0.09
    åĩłåIJį
    0.09
    èĪ±
    0.09
    æĻļéĹ´
    0.09
    à²Ł
    0.09
    è¾¹éĻħ
    0.08
     Zag
    0.08
    é«ĺåĩº
    0.08
    _rm
    0.08
    Activations Density 0.229%

    No Known Activations