© 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. 33568
    Prev
    Next
    INDEX
    Explanations

    upstream and downstream directions

    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
    ÅĽnie
    -0.08
    ÛĮات
    -0.08
    балан
    -0.08
     Ñģобой
    -0.08
    ftype
    -0.08
    tagName
    -0.08
    à¹Ħà¸Ĺย
    -0.08
    zelf
    -0.08
    umba
    -0.08
    veau
    -0.08
    POSITIVE LOGITS
    /down
    0.12
    -most
    0.09
    ward
    0.08
    äºĨ
    0.08
    θεν
    0.08
    er
    0.07
    ers
    0.07
    -facing
    0.07
    /off
    0.07
    åĴĮä¸Ń
    0.07
    Activations Density 0.018%

    No Known Activations