© 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. 27632
    Prev
    Next
    INDEX
    Explanations

    if is

    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
    ä¾łä¼ł
    -0.07
    iration
    -0.07
    csr
    -0.07
     centra
    -0.07
    èĭ¦è¾£
    -0.07
     rop
    -0.06
    è¯ĿæĿ¥
    -0.06
    prises
    -0.06
    .cls
    -0.06
    å¦Ĥæŀľæĥ³è¦ģ
    -0.06
    POSITIVE LOGITS
    åģļåĪ°äºĨ
    0.11
    èĥ½åģļåĪ°
    0.09
    åľ¨è¿Ļæĸ¹éĿ¢
    0.09
    åı¯ä»¥åģļåĪ°
    0.09
    åģļåĪ°
    0.08
     melakukannya
    0.08
    æģ°æģ°
    0.08
    æŃ£æĺ¯
    0.08
    è¿İ
    0.07
    åijµ
    0.07
    Activations Density 0.097%

    No Known Activations