© 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. 54362
    Prev
    Next
    INDEX
    Explanations

    cheer, waved, waited

    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
    è¯ŀ
    -0.10
    æī§æĶ¿
    -0.09
    åĨħéĻĨ
    -0.09
    æ¾į
    -0.08
    åŃº
    -0.08
    å¸Ŀçİĭ
    -0.08
    ä¹¾åĿ¤
    -0.08
    é¼İ
    -0.08
    çĺ¾
    -0.08
    çĴĭ
    -0.08
    POSITIVE LOGITS
    è¯Ŀé¢ĺ
    0.09
    hya
    0.08
    _scaling
    0.08
    hy
    0.08
    izards
    0.08
    ä¸Ģæľ¬
    0.08
    lope
    0.08
    affle
    0.08
    åĤį
    0.08
    æľīä¸Ģ次
    0.08
    Activations Density 0.029%

    No Known Activations