© 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. 9953
    Prev
    Next
    INDEX
    Explanations

    best practices or recommendations

    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
    缼å¼Ģ
    -0.10
    ä¸Ģç»ı
    -0.10
    å¾Īæ·±
    -0.09
    éĽģ
    -0.09
    åģļ强
    -0.09
    åĪ°æľŁ
    -0.09
    éģįå¸ĥ
    -0.09
    pek
    -0.09
    éĨĴ
    -0.08
    åĮ®
    -0.08
    POSITIVE LOGITS
    aylor
    0.11
    cea
    0.10
    路线
    0.09
    rij
    0.08
    ä»ģ
    0.08
    jen
    0.08
    (Spring
    0.08
    ToFile
    0.08
    plat
    0.08
    çļĦæľĭåıĭ
    0.08
    Activations Density 0.023%

    No Known Activations