© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 21665
    Prev
    Next
    INDEX
    Explanations

    modern or contemporary

    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
    ä¸ŃåĽ½ä¼łç»Ł
    -0.10
    èĥĮåIJİ
    -0.09
    ÊĮ
    -0.09
    china
    -0.09
     Invocation
    -0.09
    æĻļå¹´
    -0.09
    åĩŃ
    -0.08
    thouse
    -0.08
    brush
    -0.08
    ä¼łç»Ł
    -0.08
    POSITIVE LOGITS
    ä¸įåħį
    0.09
    èĥ½æī¾åĪ°
    0.09
    å¾ģ
    0.09
    å¼łæī¬
    0.09
    çĿĢæīĭ
    0.08
    åĸĦäºİ
    0.08
    æĵħ
    0.08
    æĭľå¸Ī
    0.08
    é¾ĻéŨ
    0.08
    olu
    0.08
    Activations Density 0.047%

    No Known Activations