© 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. 10796
    Prev
    Next
    INDEX
    Explanations

    any good or different

    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
    è¿Ŀ
    -0.09
    ardi
    -0.09
    _some
    -0.09
    ä¸ĢäºĽ
    -0.08
    æĦ¿
    -0.08
    ç®Ģæĺĵ
    -0.08
    ç§Ģ丽
    -0.08
     some
    -0.08
    ENDER
    -0.08
    æľº
    -0.08
    POSITIVE LOGITS
    tit
    0.10
    æĪĹ
    0.09
    avig
    0.09
    ä¼łç»ŁçļĦ
    0.09
    pll
    0.09
    亲çĪ±çļĦ
    0.09
    ä¼łç»Łäº§ä¸ļ
    0.09
    豫
    0.09
    级以ä¸Ĭ
    0.09
    æ§ģ
    0.08
    Activations Density 0.060%

    No Known Activations