© 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. 35439
    Prev
    Next
    INDEX
    Explanations

    academic year or class standing

    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
    æ¸ħ代
    -0.10
    常年
    -0.10
    .det
    -0.09
    etter
    -0.09
    ê²Į
    -0.09
    tal
    -0.09
    erring
    -0.09
    é¤IJ
    -0.08
     Carla
    -0.08
     Alumni
    -0.08
    POSITIVE LOGITS
    åħ¶éĹ´
    0.10
    享
    0.09
    çļĦ表çİ°
    0.09
    ä¼Ĭæĸ¯
    0.09
    对åŃ©åŃIJ
    0.08
    åĬª
    0.08
     Pis
    0.08
    åı²è¯Ĺ
    0.08
    è¡Įäºĭ
    0.08
    峪
    0.08
    Activations Density 0.008%

    No Known Activations