© 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. 52740
    Prev
    Next
    INDEX
    Explanations

    glitter, glittering, glittery

    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
    uez
    -0.10
    ouns
    -0.09
    ç´łåħ»
    -0.09
    luent
    -0.09
    iece
    -0.08
    ç«Ļç«ĭ
    -0.08
    ipur
    -0.08
    èį»
    -0.08
     lightning
    -0.08
    åIJı
    -0.08
    POSITIVE LOGITS
    burgh
    0.11
    cope
    0.09
    мен
    0.09
    éªijåħµ
    0.09
    ingly
    0.09
    astic
    0.09
    wich
    0.08
    红èĮ¶
    0.08
    izedName
    0.08
    ÙĪجÙĩ
    0.08
    Activations Density 0.002%

    No Known Activations