© 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. 29545
    Prev
    Next
    INDEX
    Explanations

    there upon

    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
    apsed
    -0.08
    åħ¶åľ¨
    -0.07
    les
    -0.06
    VB
    -0.06
    ibi
    -0.06
    表ä¸Ń
    -0.06
    为äºĨ让
    -0.06
    IB
    -0.06
    vers
    -0.06
    auge
    -0.06
    POSITIVE LOGITS
    ä¿©
    0.12
    /her
    0.11
    æ¯ıä¸Ģ个人çļĦ
    0.10
     berdua
    0.10
    åĢĨ
    0.10
    èĢģ人家
    0.10
     οÏĢοί
    0.10
    zelf
    0.09
    unes
    0.09
    ؤÙĦاء
    0.09
    Activations Density 0.157%

    No Known Activations