© 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. 62826
    Prev
    Next
    INDEX
    Explanations

    Dwight, Shane, names ending in ane

    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
    ocha
    -0.10
    ãģİ
    -0.10
    åħ®
    -0.09
    otted
    -0.09
    ICODE
    -0.09
    alling
    -0.09
    è¿Ń
    -0.08
    coh
    -0.08
    æĩĭ
    -0.08
    _CSR
    -0.08
    POSITIVE LOGITS
    uations
    0.10
    ãģĵãģ¨ãģĮãģ§ãģįãĤĭ
    0.09
    aus
    0.09
    çIJĨåıij
    0.09
    åIJIJ
    0.08
    ä¸įæĸŃæıIJé«ĺ
    0.08
    ãģĵãģ¨ãģĮãģ§ãģį
    0.08
    bred
    0.08
    OfMonth
    0.08
    èĽĨ
    0.08
    Activations Density 0.003%

    No Known Activations