© 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. 45054
    Prev
    Next
    INDEX
    Explanations

    Nick name

    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
    ivec
    -0.08
    emuk
    -0.08
    cene
    -0.08
     sscanf
    -0.08
    åĽłäºº
    -0.07
    __;
    -0.07
    __:
    -0.07
    alj
    -0.07
     saturn
    -0.07
    ][(
    -0.07
    POSITIVE LOGITS
    strict
    0.09
     strict
    0.08
    ä¸¥æł¼
    0.08
     strictly
    0.08
    å¿ħé¡»æĺ¯
    0.07
     непÑĢеменно
    0.07
     necessarily
    0.07
     explicitly
    0.07
    ä¸įå¾Ĺ
    0.06
    æģĴ
    0.06
    Activations Density 0.027%

    No Known Activations