© 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. 16439
    Prev
    Next
    INDEX
    Explanations

    version numbers (e.g., 7, 3, 4, 5)

    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
    个æľĪåĨħ
    -0.07
    人åĪ°
    -0.07
    èĬĤçļĦ
    -0.07
    æĻļé¥Ń
    -0.07
    个æľĪåIJİ
    -0.07
    kje
    -0.07
    ê³ĦìĹIJ
    -0.07
    lap
    -0.06
    êu
    -0.06
    æ¸ħç®Ĺä¿¡æģ¯
    -0.06
    POSITIVE LOGITS
    -era
    0.11
    .x
    0.08
    åıĬ以ä¸Ĭ
    0.08
    æĹ¶æľŁçļĦ
    0.07
    etus
    0.07
    enn
    0.07
    以åīįçļĦ
    0.07
     version
    0.07
    以æĿ¥çļĦ
    0.07
    æĪĸ以ä¸Ĭ
    0.07
    Activations Density 0.392%

    No Known Activations