© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 22861
    Prev
    Next
    INDEX
    Explanations

    is your

    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
    åĽłä¸ºå®ĥ
    -0.09
    elman
    -0.09
    دÙħ
    -0.09
    鹤
    -0.09
    bero
    -0.09
    YA
    -0.08
    æŃĮèĪŀ
    -0.08
     liners
    -0.08
    Markers
    -0.08
    éĽĨä¸Ńåľ¨
    -0.08
    POSITIVE LOGITS
    isko
    0.10
    çļĦ强大
    0.09
    ephir
    0.09
    ç»ĦåĽ¢
    0.08
    以èī²
    0.08
    mers
    0.08
    ç§ĭåĨ¬
    0.08
    好åĿı
    0.08
    hic
    0.08
    icated
    0.08
    Activations Density 0.028%

    No Known Activations