© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 19959
    Prev
    Next
    INDEX
    Explanations

    story file names

    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
    ilon
    -0.09
    avor
    -0.09
    ayout
    -0.08
    çªĿ
    -0.08
    åľ¨ä»Ĭå¹´
    -0.08
    most
    -0.08
    Ä±ÅŁ
    -0.08
    à¸ģร
    -0.08
     timeval
    -0.07
    æĸĩåĮĸåĴĮ
    -0.07
    POSITIVE LOGITS
     commons
    0.09
    åĩºæ±Ĺ
    0.09
    èİ·æĤī
    0.09
    å·²ç»ıè¶ħè¿ĩ
    0.09
    æī¿æİ¥
    0.09
    æīĭ表
    0.09
    geme
    0.09
     Pru
    0.08
    åģı
    0.08
    OutOfRangeException
    0.08
    Activations Density 0.001%

    No Known Activations