© 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. 23864
    Prev
    Next
    INDEX
    Explanations

    hand phrases

    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
    amt
    -0.10
    èĨĽ
    -0.10
    念头
    -0.10
    eger
    -0.10
    éĵĻ
    -0.09
    èİ·å¾ĹæĦŁ
    -0.09
    ç«ĭä½ĵ
    -0.09
    elves
    -0.09
    åįģæĿ¡
    -0.09
    AtPath
    -0.09
    POSITIVE LOGITS
    ä¸Ģæīĭ
    0.10
     hand
    0.09
     Hand
    0.09
    æį£
    0.08
    ache
    0.08
    ç¾İ好çĶŁæ´»
    0.08
    æĬ½
    0.08
    æIJı
    0.08
    åĽ¾æĸĩ
    0.08
    angu
    0.08
    Activations Density 0.014%

    No Known Activations