© 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. 2065
    Prev
    Next
    INDEX
    Explanations

    publish or published content

    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
    çŁ³åĮĸ
    -0.10
    isman
    -0.10
    åĬłåĪĨ
    -0.10
    åĵģ
    -0.09
    ç»ıèIJ¥æ´»åĬ¨
    -0.09
    红æĹĹ
    -0.09
    å·¥ä¼ļ
    -0.09
     bip
    -0.09
    å£ģ
    -0.08
    од
    -0.08
    POSITIVE LOGITS
    ç»ĵ
    0.09
    åĪį
    0.09
     thought
    0.09
    äº®çĽ¸
    0.08
    (crate
    0.08
    esp
    0.08
    blas
    0.08
    fä
    0.08
     ÑĦин
    0.08
    ella
    0.08
    Activations Density 0.050%

    No Known Activations