© 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. 10870
    Prev
    Next
    INDEX
    Explanations

    comic book characters

    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
    éĢĬ
    -0.10
    å¼ij
    -0.09
    èĨij
    -0.08
    inactive
    -0.08
    æŃ»åĪij
    -0.08
    elda
    -0.08
    oser
    -0.08
    ugen
    -0.08
    çľģæĶ¿åºľ
    -0.08
     Ple
    -0.08
    POSITIVE LOGITS
    åīįéĢĶ
    0.11
    Qualified
    0.10
    æĶ¶çº³
    0.09
     ì²ĺ
    0.09
    æĪIJåijĺ
    0.09
    OptionsMenu
    0.09
    ä¸Ģåij³
    0.08
    ulary
    0.08
    æĭ¬
    0.08
    妻
    0.08
    Activations Density 0.047%

    No Known Activations