© 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. 38585
    Prev
    Next
    INDEX
    Explanations

    newspaper 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
    brush
    -0.09
     Gabri
    -0.09
    Dismiss
    -0.08
    pped
    -0.08
    åľºä¸Ĭ
    -0.08
    erton
    -0.08
    è§Ĥ
    -0.08
    KÄ°
    -0.08
    æĸĩç«łæĿ¥æºIJ
    -0.08
    éħ¿éĢł
    -0.08
    POSITIVE LOGITS
    é»ı
    0.09
    ainment
    0.09
    apixel
    0.08
    çĸĻ
    0.08
    _NB
    0.08
    yps
    0.08
    çĵ£
    0.08
    åŀ¤
    0.08
    åİļåİļ
    0.08
    æĸĩåĮĸä¼łåªĴ
    0.08
    Activations Density 0.002%

    No Known Activations