© 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. 50848
    Prev
    Next
    INDEX
    Explanations

    code block delimiters

    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
    uban
    -0.07
    hev
    -0.07
     duer
    -0.06
    noinspection
    -0.06
     coordinated
    -0.06
    aul
    -0.06
    ag
    -0.06
    én
    -0.06
     himself
    -0.06
    åİĭæł¹
    -0.06
    POSITIVE LOGITS
    <|box_end|>
    0.08
    szt
    0.08
    antal
    0.08
    ÅŁk
    0.08
    _NATIVE
    0.08
    znak
    0.07
    .notes
    0.07
    LEGRO
    0.07
    elih
    0.07
     Envir
    0.07
    Activations Density 0.009%

    No Known Activations