© 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. 34429
    Prev
    Next
    INDEX
    Explanations

    look like or looks positive

    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
     flatt
    -0.09
    kre
    -0.08
    å¦ĤæĦı
    -0.08
    .localized
    -0.08
    è¹ĭ
    -0.08
    ä¸Ģ度
    -0.08
    umba
    -0.08
    éļľ
    -0.08
     بص
    -0.08
    ä¸ĭè¾¾
    -0.08
    POSITIVE LOGITS
    å¤ĸ表
    0.11
    çĻ½èī²çļĦ
    0.10
    ä¸Ģå¹ħ
    0.09
    泡
    0.09
    å§ĭç»Īä¿ĿæĮģ
    0.09
    éķ¿å¾Ĺ
    0.09
    æĿ¡
    0.09
    éĩľ
    0.09
    ä¸Ģçľ¼
    0.09
    jem
    0.09
    Activations Density 0.113%

    No Known Activations