© 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. 56585
    Prev
    Next
    INDEX
    Explanations

    none 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
    resse
    -0.09
     only
    -0.09
    æŁIJç§į
    -0.09
    é£İæ°Ķ
    -0.08
     uncon
    -0.08
     not
    -0.08
    åĦĴ
    -0.08
    ä¸Ģ个æĸ°çļĦ
    -0.08
    å¤ļç§įå½¢å¼ı
    -0.08
    еÑģп
    -0.08
    POSITIVE LOGITS
    theless
    0.16
    raf
    0.10
    igator
    0.10
    isy
    0.10
    erg
    0.10
    owing
    0.09
    æļ¾
    0.09
    æ·
    0.09
    dem
    0.09
    æĪĸå¤ļ
    0.09
    Activations Density 0.013%

    No Known Activations