© 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. 22097
    Prev
    Next
    INDEX
    Explanations

    .NET Foundation

    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
    s
    -0.11
    urs
    -0.09
    ieren
    -0.09
    ç¾½
    -0.08
     cáºŃn
    -0.08
    ä¹ĭæĥħ
    -0.08
    æľ¬é¢Ĩ
    -0.08
    wap
    -0.08
    ÙĨاÙĨ
    -0.08
    erc
    -0.08
    POSITIVE LOGITS
    efore
    0.10
    -unstyled
    0.10
    oris
    0.10
    itor
    0.09
    áIJŁ
    0.09
    æ¡Ĩ
    0.09
    iÅŁ
    0.09
    ially
    0.09
    TRS
    0.09
    åŃIJéĩĮ
    0.08
    Activations Density 0.122%

    No Known Activations