© 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. 52596
    Prev
    Next
    INDEX
    Explanations

    authors for code and documentation

    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
    çīĪæĿĥå½Ĵ
    -0.09
    便æĺ¯
    -0.09
    å¿¿
    -0.09
    esen
    -0.09
    iban
    -0.09
    logo
    -0.09
    èĢĮè¿Ļ
    -0.08
    assin
    -0.08
    å®ī举
    -0.08
    åĵ²
    -0.08
    POSITIVE LOGITS
    æĸ«
    0.09
    åĽ¢
    0.09
    hoot
    0.09
    éĥ½æľīçĿĢ
    0.08
    è§ĦèĮĥåĮĸ
    0.08
    级åĪ«
    0.08
    prox
    0.08
    çīµ
    0.08
    CurrentValue
    0.08
    ä¸ĭåıij
    0.08
    Activations Density 0.162%

    No Known Activations