© 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. 6605
    Prev
    Next
    INDEX
    Explanations

    battle and status updates

    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
    licant
    -0.10
    æ¼ī
    -0.10
    iona
    -0.09
    pper
    -0.09
    太åIJİ
    -0.09
     Boeh
    -0.09
    åīĽ
    -0.09
    è¶Ĭé«ĺ
    -0.08
    å¾·å°Ķ
    -0.08
     Holidays
    -0.08
    POSITIVE LOGITS
     дейÑģÑĤвиÑı
    0.10
     battle
    0.10
    æĪĺæĸĹ
    0.09
     Battle
    0.09
    åıĹ害
    0.09
    æĮģèĤ¡
    0.09
    çĸ¾
    0.09
    Battle
    0.09
    åºŃ
    0.09
    okens
    0.08
    Activations Density 0.067%

    No Known Activations