© 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. 4427
    Prev
    Next
    INDEX
    Explanations

    explanation for

    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
    ä¸ĢåĿĹ
    -0.09
    ðŁijĪ
    -0.09
    åįłæľī
    -0.08
    æ¦ľæł·
    -0.08
    绣çŃ¹æİ¨è¿Ľ
    -0.08
     Gron
    -0.08
     Sloan
    -0.08
     Ø£Ùħر
    -0.08
    æĮ¡
    -0.08
    åIJij社ä¼ļ
    -0.08
    POSITIVE LOGITS
    deen
    0.10
    ä¼ļéķ¿
    0.10
    íķĺê²łìĬµëĭĪëĭ¤
    0.09
    åħ³äºİ
    0.09
    idget
    0.09
    uckle
    0.09
    ãģ§ãģĬ
    0.09
    为æĤ¨
    0.08
    æĪijä¼ļ
    0.08
    çľĭä½ł
    0.08
    Activations Density 0.032%

    No Known Activations