© 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. 49245
    Prev
    Next
    INDEX
    Explanations

    change without notice

    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
    被æ·ĺæ±°
    -0.10
    ä¸įè¦ģåĨį
    -0.10
    æĺ¯æĪijåĽ½
    -0.09
    å²³
    -0.09
    ç¥ļ
    -0.09
    amp
    -0.08
    鼶
    -0.08
    ä¸ĢåĪĩéĥ½
    -0.08
    çİ°å·²
    -0.08
    åĴĴ
    -0.08
    POSITIVE LOGITS
    åıĺåĮĸ
    0.09
    езн
    0.09
    å½ĺ
    0.09
    chor
    0.09
    æ¿¡
    0.09
    å®ı大
    0.09
    /pol
    0.09
    å¹´å¤ľ
    0.09
     changes
    0.09
    ebin
    0.09
    Activations Density 0.154%

    No Known Activations