© 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. 7569
    Prev
    Next
    INDEX
    Explanations

    into differentiate cell lineages

    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
    å¤ĸæĿ¥
    -0.09
    olle
    -0.09
    auer
    -0.09
    人为
    -0.09
    rage
    -0.08
    .spi
    -0.08
    被迫
    -0.08
    åĮłå¿ĥ
    -0.08
     reversible
    -0.08
    以人为
    -0.08
    POSITIVE LOGITS
    æľĢç»Ī
    0.10
    æĪIJåŀĭ
    0.10
    å½¢æĪIJ
    0.09
    æĸ°çļĦ
    0.09
    æ¤į
    0.08
    ä¸Ģ代
    0.08
    éºĤ
    0.08
    UNS
    0.08
    ä¸ĭä¸Ģ代
    0.08
    vice
    0.08
    Activations Density 0.169%

    No Known Activations