© 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. 64969
    Prev
    Next
    INDEX
    Explanations

    position or extent

    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
    åĨįä¹Ł
    -0.07
    wend
    -0.07
    为è°ģ
    -0.07
     followed
    -0.07
    åıĪæĿ¥äºĨ
    -0.06
     bid
    -0.06
    头èĦij
    -0.06
    ä¸ĢæŶ
    -0.06
     internally
    -0.06
    nali
    -0.06
    POSITIVE LOGITS
    ä½Ĩä¸įè¦ģ
    0.10
    ä¸įåºĶ该
    0.08
    ä¸įå¾Ĺè¶ħè¿ĩ
    0.08
    ä¸ºå®ľ
    0.08
    çĽ¡éĩı
    0.08
    ä¸įè¦ģ让
    0.08
     neat
    0.08
    çķĻåĩº
    0.08
     exposing
    0.07
    ufs
    0.07
    Activations Density 0.080%

    No Known Activations