© 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. 2256
    Prev
    Next
    INDEX
    Explanations

    unified approach

    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
    erschaft
    -0.07
    ãģ¾ãģı
    -0.07
    åİ»çİ©
    -0.07
    çİ
    -0.07
    {:
    -0.07
    æ¾İ
    -0.06
     пÑĢиб
    -0.06
    æ½Ł
    -0.06
    æŀľåĨ»
    -0.06
    _CSR
    -0.06
    POSITIVE LOGITS
     cosmic
    0.08
    èªĵ
    0.08
     Salam
    0.08
    icos
    0.08
    ubic
    0.07
    é¢Ħè¨Ģ
    0.07
    é¢Ħ审
    0.07
    /mail
    0.07
     Wein
    0.07
    èįĴ
    0.06
    Activations Density 0.003%

    No Known Activations