© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 23406
    Prev
    Next
    INDEX
    Explanations

    life expectancy, land, looking, shift, threshold, keys, images

    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
    oft
    -0.07
    ç½ijéĢļ
    -0.06
    als
    -0.06
    ï¸İ
    -0.06
    TA
    -0.06
    F
    -0.05
    æĪijçĽ¸ä¿¡
    -0.05
    .named
    -0.05
     above
    -0.05
    R
    -0.05
    POSITIVE LOGITS
    好åij¢
    0.10
    ĻĤ
    0.09
    以ä¸ĭåĩł
    0.08
    åĢ¼å¾Ĺä¸ĢæıIJ
    0.08
     ÙĪÙĥÙĬÙģ
    0.08
    yec
    0.08
    ãĥ³ãĤ¸
    0.08
    JOR
    0.08
    mete
    0.08
    æĹ¶èµ·
    0.08
    Activations Density 0.073%

    No Known Activations