© 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. 20385
    Prev
    Next
    INDEX
    Explanations

    physical descriptions of body and shape

    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
    åīĥ
    -0.10
    eman
    -0.10
    èĥ¡åŃIJ
    -0.10
    é«Ń
    -0.09
    äºĭåIJİ
    -0.09
     cape
    -0.08
    rup
    -0.08
    è¿Ĥ
    -0.08
    çļĦæŶéĹ´éĩĮ
    -0.08
    æĹĦ
    -0.08
    POSITIVE LOGITS
    dre
    0.09
    anje
    0.08
    æĤĸ
    0.08
    åģļ梦
    0.08
    èĪĴ
    0.08
    digest
    0.08
    享æľī
    0.08
    åįļ主
    0.08
    _VARIABLE
    0.08
    اذ
    0.08
    Activations Density 0.020%

    No Known Activations