© 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. 54514
    Prev
    Next
    INDEX
    Explanations

    Bank Berhad

    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
    Ñĥж
    -0.09
    cover
    -0.09
     hype
    -0.08
    pla
    -0.08
    æľºåĬ¨
    -0.08
    .virtual
    -0.08
    æŁĶæĢ§
    -0.08
    èĻļæĭŁ
    -0.08
    ean
    -0.08
     Rut
    -0.08
    POSITIVE LOGITS
    æĴŃ
    0.09
    å±ķä½į
    0.09
     Tart
    0.09
    æĿĸ
    0.09
    _YUV
    0.09
    çŧ
    0.09
    URT
    0.09
    妻åŃIJ
    0.09
    é¢Ĩ
    0.08
    è¿Ľåıĸ
    0.08
    Activations Density 0.237%

    No Known Activations