© 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. 30279
    Prev
    Next
    INDEX
    Explanations

    Naga

    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
    çĦ¶æĺ¯
    -0.12
    ially
    -0.11
    Į
    -0.11
    èĩªå¦Ĥ
    -0.10
    ı
    -0.10
    ãģĤãģ£ãģ¦
    -0.10
    à¹Īาà¸Ļ
    -0.09
    ĭ
    -0.09
    ãģĤãģ£ãģŁ
    -0.09
    æĤĦçĦ¶
    -0.09
    POSITIVE LOGITS
    ging
    0.11
    åIJĦæł·
    0.10
    é¾Ł
    0.09
    hover
    0.09
    atories
    0.09
    atrix
    0.09
    Ñĩив
    0.09
    ê¹IJ
    0.09
    stoff
    0.08
    hole
    0.08
    Activations Density 0.011%

    No Known Activations