© 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. 56217
    Prev
    Next
    INDEX
    Explanations

    parenthetical information

    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
    arrass
    -0.07
    —or
    -0.07
    à¸Ħัà¸Ļ
    -0.07
    argar
    -0.06
    ctxt
    -0.06
    endar
    -0.06
    诸天
    -0.06
    öhn
    -0.06
    ÏĦια
    -0.06
    ÑĤÑı
    -0.06
    POSITIVE LOGITS
    ugi
    0.08
    ê³łëĬĶ
    0.08
    beste
    0.07
    fik
    0.07
    inge
    0.07
    emann
    0.07
    åĪĴ
    0.07
     Klos
    0.07
    elik
    0.07
    _DX
    0.07
    Activations Density 0.107%

    No Known Activations