© 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. 26040
    Prev
    Next
    INDEX
    Explanations

    create custom or own things

    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
    ubat
    -0.08
    /latest
    -0.08
    lage
    -0.08
    _MODULES
    -0.08
    loch
    -0.07
    æĬĵå®ŀ
    -0.07
    Schedulers
    -0.07
    aval
    -0.07
    cntl
    -0.07
    erton
    -0.07
    POSITIVE LOGITS
     custom
    0.19
    èĩªå®ļä¹ī
    0.17
    /custom
    0.16
    Custom
    0.16
    custom
    0.16
     Custom
    0.16
    å®ļåĪ¶
    0.15
    (custom
    0.15
     bespoke
    0.15
    .Custom
    0.15
    Activations Density 0.668%

    No Known Activations