© 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. 60490
    Prev
    Next
    INDEX
    Explanations

    identity

    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
     Mode
    -0.07
    chan
    -0.06
     Naked
    -0.06
    mode
    -0.06
    еди
    -0.06
    çĭ¬èĩªä¸Ģ人
    -0.06
    çª
    -0.06
    δη
    -0.06
    orum
    -0.06
    ä¸ĭå®ļ
    -0.06
    POSITIVE LOGITS
    OnInit
    0.08
    æĸĩåºĵ
    0.08
    allis
    0.08
     Overse
    0.08
    Transpose
    0.08
    Äįek
    0.08
    eliz
    0.07
    egger
    0.07
    ipsis
    0.07
    oper
    0.07
    Activations Density 0.002%

    No Known Activations