© 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. 61127
    Prev
    Next
    INDEX
    Explanations

    quotation marks or specific words

    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
    èģª
    -0.09
    emails
    -0.09
    emale
    -0.09
    à¹ģà¸Łà¸Ļ
    -0.09
    æ¶Ī
    -0.09
    çĽ¸ä¼ł
    -0.09
     eBook
    -0.08
    åİ»è¿ĩ
    -0.08
    ç²īä¸Ŀ
    -0.08
    definitions
    -0.08
    POSITIVE LOGITS
    æłĩæĺİ
    0.14
    注æĺİ
    0.13
    æłĩå¿Ĺ
    0.13
    æłĩè¯Ĩ
    0.13
    åŃĹæł·
    0.12
    æłĩè®°
    0.12
    表æĺİ
    0.12
    说æĺİ
    0.12
    æłĩ注
    0.11
     indicator
    0.10
    Activations Density 0.120%

    No Known Activations