© 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. 34289
    Prev
    Next
    INDEX
    Explanations

    Russian words and phrases

    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
    ä¸Ģå¦ĤæĹ¢å¾Ģ
    -0.10
    èĩªè´Ł
    -0.09
    åħ¨éĿ¢
    -0.09
    éĻIJé¢Ŀ
    -0.09
     Balt
    -0.08
    æ·±åħ¥äºĨ解
    -0.08
    é²±
    -0.08
     tÆ°á»Ŀng
    -0.08
    人为
    -0.08
    宿èĪį
    -0.08
    POSITIVE LOGITS
    é»»
    0.09
    ìĦ±
    0.09
    _SUPPORTED
    0.09
     assh
    0.09
    idis
    0.08
    _mapped
    0.08
    IEW
    0.08
    ä¸įç¦ģ
    0.08
    å°¾
    0.08
    _HEL
    0.08
    Activations Density 0.003%

    No Known Activations