© 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. 35363
    Prev
    Next
    INDEX
    Explanations

    focusing

    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
    çģµéŃĤ
    -0.09
    ãģĹãģ¾
    -0.08
    ordinal
    -0.08
    æ¼ķ
    -0.08
    onical
    -0.08
    éķ°
    -0.08
    è¦ģ说
    -0.08
    éĽĨåĽ¢èĤ¡ä»½
    -0.08
    ä¸įæĩĤ
    -0.08
     Та
    -0.08
    POSITIVE LOGITS
    criptors
    0.09
    PIO
    0.09
    à¹Į
    0.09
    ized
    0.08
    é¹ķ
    0.08
    ä¸įä½Ĩ
    0.08
    ity
    0.08
    çĶ¨åľ°
    0.08
    æĬĹè¡¡
    0.08
    umm
    0.08
    Activations Density 0.216%

    No Known Activations