© 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. 57598
    Prev
    Next
    INDEX
    Explanations

    not to mention

    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
    毫ä¸įçĬ¹è±«
    -0.10
    ä¸įèĥ½åĨį
    -0.10
    éĴ¿
    -0.09
    åķľ
    -0.09
     zwar
    -0.09
    ä¸įå¾Ĺå·²
    -0.09
    åĭģ
    -0.08
    bió
    -0.08
    æİ£
    -0.08
    ä¸įåºĶ该
    -0.08
    POSITIVE LOGITS
    rey
    0.11
    ably
    0.11
    aire
    0.10
    ette
    0.09
    æĺ¯åľ¨
    0.09
    _Db
    0.09
    éŨåīį
    0.09
    æ·±åħ¥äººå¿ĥ
    0.08
    lish
    0.08
     Gro
    0.08
    Activations Density 0.004%

    No Known Activations