© 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. 17676
    Prev
    Next
    INDEX
    Explanations

    into

    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
    ä¹ĭå¿ĥ
    -0.10
    天ä¸Ĭ
    -0.10
    æ±Ĺæ°´
    -0.09
    尾巴
    -0.09
    ä¹ĭæĥħ
    -0.09
    ç»ıèIJ¥æ´»åĬ¨
    -0.09
    çĮĽ
    -0.09
    PLIED
    -0.08
    åħħ
    -0.08
    çIJ¢
    -0.08
    POSITIVE LOGITS
     into
    0.12
    æµģåħ¥
    0.10
    into
    0.09
    仪
    0.09
     Into
    0.09
     vÃło
    0.09
    äºİä¸Ģä½ĵ
    0.09
    æİĬ
    0.08
    Into
    0.08
    离
    0.08
    Activations Density 0.051%

    No Known Activations