© 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. 35051
    Prev
    Next
    INDEX
    Explanations

    role of

    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
    éĢIJ
    -0.10
    coin
    -0.09
    æĪį
    -0.08
     tur
    -0.08
    åijĢ
    -0.08
    cale
    -0.08
    طبÙĤ
    -0.08
    inge
    -0.08
    ORM
    -0.08
    鼩
    -0.08
    POSITIVE LOGITS
    媾
    0.10
    æĸ°åĮº
    0.09
    åIJĦå¼Ĥ
    0.09
    -valu
    0.09
    å¸Ĥåİ¿
    0.09
    ä¸Ģä¼ļ
    0.09
     pomi
    0.09
     болÑĮ
    0.09
    å¤ĸåĽ´
    0.09
    abı
    0.09
    Activations Density 0.058%

    No Known Activations