© 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. 17289
    Prev
    Next
    INDEX
    Explanations

    urls with ?v= or .gl/

    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
    æĻĥ
    -0.09
    æĮģç»Ńæİ¨è¿Ľ
    -0.09
    åĨ°åĨ·
    -0.09
    åĨ³èĥľ
    -0.09
    ucky
    -0.09
    裹
    -0.08
    æĿĥåĬĽ
    -0.08
    зав
    -0.08
    è¡Ģèħ¥
    -0.08
    èĭ±çī¹
    -0.08
    POSITIVE LOGITS
    èĹı
    0.09
    æĤ£
    0.09
    èĮ¨
    0.08
    à¸Ĥà¸Ļ
    0.08
    åķ¤
    0.08
    åĺ¤
    0.08
    黼
    0.08
    bert
    0.08
    yll
    0.08
    erator
    0.08
    Activations Density 0.004%

    No Known Activations