© 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. 52802
    Prev
    Next
    INDEX
    Explanations

    are or were followed by past participles

    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
    ç«¥
    -0.10
    å°Ķæĸ¯
    -0.10
    prise
    -0.10
    .beh
    -0.09
    ãģĽ
    -0.09
    esium
    -0.09
     Rock
    -0.08
    tok
    -0.08
     Fowler
    -0.08
    åīª
    -0.08
    POSITIVE LOGITS
    tright
    0.09
    åħ¶ä»ĸçļĦ
    0.09
    æªĢ
    0.08
    è¤IJ
    0.08
    ijo
    0.08
    .Attach
    0.08
    åıĹåĪ°äºĨ
    0.08
    _constraints
    0.08
    è´Łè´£
    0.08
    Ast
    0.07
    Activations Density 0.174%

    No Known Activations