© 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. 1441
    Prev
    Next
    INDEX
    Explanations

    towing and propelled vehicles

    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
    æĹģ
    -0.10
    oose
    -0.09
     TSA
    -0.09
    ALAR
    -0.09
     scand
    -0.09
    _kw
    -0.08
    sid
    -0.08
    æīĭå¥Ĺ
    -0.08
    æµı
    -0.08
    丹
    -0.08
    POSITIVE LOGITS
    æĸ¤
    0.11
    æģ¤
    0.10
    è´¨éĩıåĴĮ
    0.10
    coni
    0.10
    ä¸Ģå¤ľ
    0.09
    åı£ä¸Ń
    0.09
    èĤ²
    0.09
    å©ļ礼
    0.09
    éĿ¢è²Į
    0.09
    orage
    0.09
    Activations Density 0.059%

    No Known Activations