© 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. 53461
    Prev
    Next
    INDEX
    Explanations

    in [preposition]

    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
    ä¸İæŶ
    -0.10
    污
    -0.09
    lood
    -0.08
    åĮ¹
    -0.08
     orig
    -0.08
    éļľ
    -0.08
    æ´µ
    -0.08
    cel
    -0.08
     Deliver
    -0.08
    åĨĴçĿĢ
    -0.08
    POSITIVE LOGITS
    éĶ»éĢł
    0.09
     prophets
    0.09
    itre
    0.08
    澧
    0.08
    gage
    0.08
    KER
    0.08
    ãģįãģŁ
    0.08
    ило
    0.08
    èĥª
    0.08
    æīĵåĮħ
    0.08
    Activations Density 0.014%

    No Known Activations