© 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. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 33482
    Prev
    Next
    INDEX
    Explanations

    historical comparisons and contrasts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ä¹ŁæľīåĪ©äºİ
    -0.08
    åħĪåIJİåľ¨
    -0.08
    éĹ®é¢ĺæŶ
    -0.08
    éĹ®é¢ĺæĺ¯
    -0.07
    æĿ¥å¾Ĺ
    -0.07
    ä¼łçļĦ
    -0.07
    ç»ĺ
    -0.07
    æĢİä¹Īåģļ
    -0.07
    ibold
    -0.07
    à¹Ģสà¸Ļ
    -0.07
    POSITIVE LOGITS
    æ®Ĭ
    0.08
    åĬłä»¥
    0.08
    æİ°
    0.07
     overlap
    0.07
    çĥĽ
    0.07
    移
    0.06
     overlay
    0.06
    lai
    0.06
    å°±æѤ
    0.06
    å·§å¦Ļåľ°
    0.06
    Activations Density 0.371%

    No Known Activations