© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 11765
    Prev
    Next
    INDEX
    Explanations

    is a

    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
    adir
    -0.07
    ULD
    -0.07
    Ø·ÙĬÙĨ
    -0.07
     Hayes
    -0.06
    rott
    -0.06
    pond
    -0.06
    _equiv
    -0.06
    à¸ĵะ
    -0.06
     Procur
    -0.06
    bió
    -0.06
    POSITIVE LOGITS
    <|box_end|>
    0.07
    åħį
    0.07
    zis
    0.07
    åħ·åIJĪ
    0.07
    表æĺİ
    0.06
    ãĤĤãģ¨
    0.06
    azol
    0.06
    yms
    0.06
    veys
    0.06
    åijĺ
    0.06
    Activations Density 0.028%

    No Known Activations