© 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. 1523
    Prev
    Next
    INDEX
    Explanations

    programming constructs and specific words

    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
    zilla
    -0.09
    翼翼
    -0.09
    ighbors
    -0.09
    सार
    -0.08
    urig
    -0.08
    ation
    -0.08
    ousel
    -0.08
    리ì¦ĺ
    -0.08
    ÙĪص
    -0.08
    æľīåĬł
    -0.08
    POSITIVE LOGITS
    å§ĭèĩ³ç»Ī
    0.12
    ä¸ĵäººè´Łè´£
    0.11
    éĥ¨åĪĨç»ĦæĪIJ
    0.09
    åĬ©äºİ
    0.09
    “
    0.08
    ly
    0.08
    ä»ĸæĿ¥
    0.08
    大åĪ°
    0.08
    æŃ¤èµ·
    0.08
    以ä¸ĭæĸ¹å¼ı
    0.08
    Activations Density 0.001%

    No Known Activations