© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 52613
    Prev
    Next
    INDEX
    Explanations

    list properties, sorting, folders

    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
    æ¼Ĩ
    -0.09
    çģµæ°Ķ
    -0.09
    èį¦
    -0.08
    íĥķ
    -0.08
     lineno
    -0.08
    .libs
    -0.08
    lineno
    -0.08
    zan
    -0.08
    ä¸įå¾Ĺä¸į
    -0.08
    为æĤ¨æıIJä¾Ľ
    -0.08
    POSITIVE LOGITS
    ä¸Ģæŀļ
    0.10
    mates
    0.09
    æĺķ
    0.09
    ×ķת
    0.09
    enant
    0.09
    æĴĩ
    0.09
    amente
    0.09
    ipated
    0.09
    UEST
    0.09
    饼
    0.09
    Activations Density 0.063%

    No Known Activations