© 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. 38320
    Prev
    Next
    INDEX
    Explanations

    output parameters or keywords

    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
     Rasul
    -0.08
    erton
    -0.07
    ely
    -0.07
    ily
    -0.06
    ka
    -0.06
    .removeChild
    -0.06
    imers
    -0.06
    áĥĺáĥĽ
    -0.06
    é£İæĻ¯çº¿
    -0.06
    ovid
    -0.06
    POSITIVE LOGITS
    InOut
    0.09
    [out
    0.08
     out
    0.08
    cratch
    0.08
    ToArray
    0.08
    templ
    0.08
    丼
    0.08
    /save
    0.07
    [:]
    0.07
    номи
    0.07
    Activations Density 0.164%

    No Known Activations