© 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. 53610
    Prev
    Next
    INDEX
    Explanations

    catch, score, land, grab

    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
    pent
    -0.10
    ooter
    -0.10
    ä½Ĩä¸įéĻIJäºİ
    -0.10
    inia
    -0.09
    din
    -0.09
     Turnbull
    -0.09
    .story
    -0.09
     Yates
    -0.09
    å¾Ģå¤ĸ
    -0.08
    ç´§ç´§åĽ´ç»ķ
    -0.08
    POSITIVE LOGITS
    ä¸ĢæĬĬ
    0.10
    æĹĦ
    0.09
    äºĨä¸Ģ份
    0.09
    ä¸Ģ份
    0.08
    é«ĺä»·
    0.08
    à¹ĥà¸ļ
    0.08
    efore
    0.08
    olan
    0.08
    losure
    0.08
    ä¸Ģ个好çļĦ
    0.08
    Activations Density 0.016%

    No Known Activations