© 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. 10988
    Prev
    Next
    INDEX
    Explanations

    ambient conditions

    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
    astics
    -0.10
    çīĩåĮº
    -0.09
    erna
    -0.09
    naire
    -0.09
    anh
    -0.09
    ãģ¾ãģĤ
    -0.09
    é¡¿
    -0.09
    æķĸ
    -0.09
    便ç§ĺ
    -0.09
    é¦ĭ
    -0.09
    POSITIVE LOGITS
    主ä¹īèĢħ
    0.10
    ï¸
    0.09
    äºĨ大éĩıçļĦ
    0.09
    ä¿Ł
    0.09
    NESS
    0.09
    äºĨäºĽ
    0.08
    åħŃåIJĪ
    0.08
     distr
    0.08
    çªĥ
    0.08
    ulance
    0.08
    Activations Density 0.017%

    No Known Activations