© 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. 4770
    Prev
    Next
    INDEX
    Explanations

    transportation service

    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
    å¿Ŀ
    -0.10
    è´§æŀ¶
    -0.10
    çłĮ
    -0.10
    空åĨĽ
    -0.09
    æ³³
    -0.09
    天çĮ«
    -0.09
    鼶åĶ®åķĨ
    -0.09
    æķķ
    -0.09
    俯
    -0.09
    .precision
    -0.08
    POSITIVE LOGITS
    æľįåĬ¡è´¨éĩı
    0.12
    çļĦæľįåĬ¡
    0.12
    驾驶åijĺ
    0.12
    ä¹ħ
    0.11
    åĴĮæľįåĬ¡
    0.10
    åı¸æľº
    0.10
     service
    0.10
    è½½
    0.10
    æİ¥éĢģ
    0.10
    交éĢļå®īåħ¨
    0.10
    Activations Density 0.076%

    No Known Activations