© 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. 49037
    Prev
    Next
    INDEX
    Explanations

    New York Giants or San Francisco Giants

    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
    ãģıãĤĮ
    -0.11
    sing
    -0.10
    sar
    -0.10
    sWith
    -0.10
    onaut
    -0.10
    ski
    -0.09
     Skate
    -0.09
    ieren
    -0.09
    rist
    -0.09
    sie
    -0.08
    POSITIVE LOGITS
    esses
    0.11
    -hearted
    0.11
    룰
    0.09
    ows
    0.09
    çĿĢçľ¼äºİ
    0.09
    /problems
    0.09
    lijk
    0.09
    æ´»åĬ¨çİ°åľº
    0.09
    èį¯ä¸ļ
    0.09
     propTypes
    0.09
    Activations Density 0.013%

    No Known Activations