© 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. 22587
    Prev
    Next
    INDEX
    Explanations

    certain

    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
    èĤ¯
    -0.07
     Banj
    -0.07
    intas
    -0.06
    kh
    -0.06
    xB
    -0.06
    äºĶä½į
    -0.06
    çºĮ
    -0.06
    -strip
    -0.06
    éĿĸ
    -0.06
    죽
    -0.06
    POSITIVE LOGITS
     certain
    0.10
    æŁIJäºĽ
    0.10
    ertain
    0.09
    æŃ»è§Ĵ
    0.08
    éĻ¤éĿŀ
    0.08
     certains
    0.08
    bok
    0.08
     Mondays
    0.07
    ç§ķ
    0.07
    unless
    0.07
    Activations Density 0.161%

    No Known Activations