© 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. 9473
    Prev
    Next
    INDEX
    Explanations

    list of types

    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
    ksen
    -0.08
    å°½èĩªå·±
    -0.07
    ingos
    -0.07
    ajs
    -0.07
    åłĤåłĤ
    -0.07
    kins
    -0.07
    çģµçļĦ
    -0.07
    ette
    -0.07
    amkan
    -0.07
    è¿ĶåĽŀ顶éĥ¨
    -0.06
    POSITIVE LOGITS
    меÑģÑĤи
    0.08
    usanne
    0.08
    ä¸Ģ模
    0.07
    خاÙĨÙĩ
    0.07
    ↵↵↵↵↵↵↵↵↵↵
    0.07
    æŁĵ
    0.07
    è°ģéĥ½
    0.07
    acos
    0.07
    åħ¨æĺ¯
    0.07
    åľ£è´¤
    0.07
    Activations Density 0.017%

    No Known Activations