© 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. 50272
    Prev
    Next
    INDEX
    Explanations

    vantage point or standpoint

    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
    åĩºäºİ
    -0.08
    代表大ä¼ļ
    -0.08
    裾
    -0.08
    iffin
    -0.08
    agogue
    -0.07
    idor
    -0.07
    ä¸ĭéĿ¢æĺ¯
    -0.07
    icals
    -0.07
    è¿Ļæł·çļĦè¯Ŀ
    -0.07
    çĽħ
    -0.07
    POSITIVE LOGITS
    æľĽåİ»
    0.13
    è§ĤæľĽ
    0.11
    ç¼¢
    0.11
    ted
    0.10
     Äijả
    0.10
    osition
    0.10
    åĬĽéĩı
    0.10
    çŀ»
    0.10
    åĨ·åĨ·
    0.09
     hÆ°á»Łng
    0.09
    Activations Density 0.004%

    No Known Activations