© 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. 3534
    Prev
    Next
    INDEX
    Explanations

    connected to or with

    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
    ogle
    -0.09
    产
    -0.09
    nal
    -0.08
    çĩĥçħ¤
    -0.08
    çľ¼éĩĮ
    -0.08
    ãģ»ãģ©
    -0.08
     Spit
    -0.08
     Gri
    -0.08
     Buk
    -0.08
    æłĭ
    -0.08
    POSITIVE LOGITS
    æīĵ交éģĵ
    0.09
    apos
    0.09
    ä¸īåĨľ
    0.09
    åIJij社ä¼ļ
    0.09
    lest
    0.09
    IMO
    0.08
    voy
    0.08
    åľ¨ä¸Ģèµ·
    0.08
    æĸ¹æĸ¹éĿ¢éĿ¢
    0.08
    Äı
    0.08
    Activations Density 0.107%

    No Known Activations