© 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. 61532
    Prev
    Next
    INDEX
    Explanations

    donate help support

    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
    çªģ
    -0.10
    ë°Ľ
    -0.10
    ÙĨس
    -0.09
    íı¬
    -0.09
    ndl
    -0.09
    祥
    -0.08
    éħ¥
    -0.08
     пока
    -0.08
    åĭ¤
    -0.08
    ãģĹãģ
    -0.08
    POSITIVE LOGITS
    çľ¼éĥ¨
    0.10
    æĪĸå¤ļæĪĸå°ij
    0.09
    å¿ĥ缮ä¸Ń
    0.09
    å´ĸ
    0.09
    è¿Ļ家åħ¬åı¸
    0.09
    è¿ĺè®°å¾Ĺ
    0.09
    æĪij家
    0.08
    çĤ¹æ»´
    0.08
    å®ļåIJij
    0.08
    伸åĩº
    0.08
    Activations Density 0.041%

    No Known Activations