© 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. 21990
    Prev
    Next
    INDEX
    Explanations

    sumptuous, fabulous, scrupulous

    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
    estation
    -0.09
    举åĬ¨
    -0.08
    -plugin
    -0.08
    çļ¿
    -0.08
    éĹŃ
    -0.08
     pomp
    -0.08
    stab
    -0.08
     sorte
    -0.08
     sometime
    -0.08
    ign
    -0.08
    POSITIVE LOGITS
    رÙĬ
    0.09
    人家
    0.09
    ERO
    0.09
    é³Į
    0.08
    eer
    0.08
    ì²ĺ
    0.08
    å®ħ
    0.08
    ello
    0.08
    imizer
    0.08
    posium
    0.08
    Activations Density 0.002%

    No Known Activations