© 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. 56374
    Prev
    Next
    INDEX
    Explanations

    anniversary of

    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
    åĬĽæ±Ĥ
    -0.10
    ÑģÑħод
    -0.09
    ä¸įåĩº
    -0.08
    ãĤĴãģĬ
    -0.08
    ç»ĪçĶŁ
    -0.08
    æ°¢
    -0.08
    æĤĶ
    -0.08
    æµ·æ·Ģ
    -0.08
    otti
    -0.08
    instein
    -0.08
    POSITIVE LOGITS
    æŃ»äº¡
    0.11
    è¯ŀçĶŁ
    0.09
    éĺĶ
    0.09
     ведÑĮ
    0.09
    ÑĢÑĥд
    0.09
    æł¸å¿ĥåĮº
    0.09
    以ä¾Ĩ
    0.08
    atu
    0.08
    æīĵå¾Ĺ
    0.08
    åħ¼
    0.08
    Activations Density 0.019%

    No Known Activations