© 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. 37363
    Prev
    Next
    INDEX
    Explanations

    filesystems, partitions, and operating systems

    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
    ç¿»
    -0.08
    ä»ķ
    -0.08
    åŁķ
    -0.08
     Gloss
    -0.08
    WEBPACK
    -0.08
    ç©´
    -0.08
    dana
    -0.08
    èģĶæĥ³
    -0.08
    æĪĴ
    -0.08
     racks
    -0.08
    POSITIVE LOGITS
    uale
    0.10
     ведÑĮ
    0.10
    没人
    0.10
    isol
    0.09
    ä¹ĺçĶ¨è½¦
    0.09
    åģĥ
    0.09
    æľķ
    0.09
    箸
    0.09
    好äºĨ
    0.09
    å´©æºĥ
    0.09
    Activations Density 0.117%

    No Known Activations