© 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. 33324
    Prev
    Next
    INDEX
    Explanations

    El Niño, XL Pipeline

    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
    odem
    -0.09
    adia
    -0.08
    ém
    -0.08
    ucha
    -0.08
    Ñī
    -0.08
    çݰ代
    -0.08
    åĬ¡
    -0.07
    ä¸ĢåĽ¢
    -0.07
    HEMA
    -0.07
    .TryParse
    -0.07
    POSITIVE LOGITS
    æħĭ
    0.10
    è¿ĩåIJİ
    0.10
    失
    0.09
     vmax
    0.09
     Giz
    0.08
    illas
    0.08
    éªĬ
    0.08
    ä¿Ĺè¯Ŀ说
    0.08
    浪潮
    0.08
    è¿ĻæŶåĢĻ
    0.08
    Activations Density 0.008%

    No Known Activations