© 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. 27617
    Prev
    Next
    INDEX
    Explanations

    well named for

    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
    éĤ£ç§į
    -0.11
    esa
    -0.10
    å¤įæ´»
    -0.10
    ESA
    -0.10
    ìŀĶ
    -0.10
    ä¼Łå¤§çļĦ
    -0.09
    æĶĴ
    -0.09
    ä¿Ĺ
    -0.09
    佩
    -0.09
    æĺ¯ä¸Ģ项
    -0.09
    POSITIVE LOGITS
    çĴĭ
    0.09
    毯
    0.08
    æįī
    0.08
    OOK
    0.08
    éĢ¯
    0.08
    pler
    0.08
    åIJŀåĻ¬
    0.07
    bic
    0.07
     figur
    0.07
    åį´ä¸į
    0.07
    Activations Density 0.145%

    No Known Activations