© 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. 57384
    Prev
    Next
    INDEX
    Explanations

    sponsor a person or animal

    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
    å±ħ
    -0.09
    .docs
    -0.09
    è¸ı
    -0.09
    èĶ·
    -0.08
    æīįæĺ¯
    -0.08
    å¨ĺ
    -0.08
    æ¦Ĩ
    -0.08
    باÙĦ
    -0.08
     everywhere
    -0.08
    .getDocument
    -0.08
    POSITIVE LOGITS
    鸣
    0.10
    æķ´ä¸ª
    0.10
    ç©·
    0.10
    åĪĨ管
    0.10
    ä¼ŀ
    0.09
    ìĦĿ
    0.09
    é¢Ĩè¡Ķ
    0.09
    hood
    0.09
    é³
    0.09
    nosis
    0.09
    Activations Density 0.016%

    No Known Activations