© 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. 52374
    Prev
    Next
    INDEX
    Explanations

    staff report

    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
    æģĴ
    -0.11
    çĦ°
    -0.09
    çĽİ
    -0.09
    èĩªç§°
    -0.08
     deb
    -0.08
    éĬ®
    -0.08
    åİŁåĽłä¹ĭä¸Ģ
    -0.08
    ç½ijç»ľä¼łæĴŃ
    -0.08
    ç«Ļèµ·æĿ¥
    -0.08
    illo
    -0.08
    POSITIVE LOGITS
    æģ¬
    0.09
    客
    0.09
    zug
    0.08
    åĨ·åĨ·
    0.08
    _heading
    0.08
    .sd
    0.08
    åĬłå·¥åİĤ
    0.08
    æļij
    0.08
    atti
    0.08
    æĪĽ
    0.08
    Activations Density 0.086%

    No Known Activations