© 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. 3298
    Prev
    Next
    INDEX
    Explanations

    earlier this month/year/week/summer

    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
    upp
    -0.09
    ä¸Ģå®ļçļĦ
    -0.09
    å®Įæķ´æĢ§
    -0.09
    ä¸Ģå®ļç¨ĭ度
    -0.09
    iming
    -0.08
     sẵ
    -0.08
    å¾Īå¤ļæŶåĢĻ
    -0.08
    æĽ·
    -0.08
    osoph
    -0.08
    çī¹å®ļ
    -0.08
    POSITIVE LOGITS
    eland
    0.09
    æĥ°
    0.09
    æľĪèĩ³
    0.09
    month
    0.09
    è·Łä¸įä¸Ĭ
    0.08
    etz
    0.08
    oard
    0.08
    æĪijçŁ¥éģĵ
    0.08
     Pres
    0.08
    æŀĦæĢĿ
    0.08
    Activations Density 0.011%

    No Known Activations