© 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. 27135
    Prev
    Next
    INDEX
    Explanations

    space and quantification

    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
    "—
    -0.07
    åĵĪéĩĮ
    -0.07
    .pag
    -0.07
    arat
    -0.07
    keer
    -0.07
    ÙĥÙĬÙģ
    -0.07
    oglio
    -0.07
    /win
    -0.07
    'er
    -0.06
    ourn
    -0.06
    POSITIVE LOGITS
    ymar
    0.08
    ycin
    0.07
    BlockSize
    0.07
    воз
    0.07
    оÑĤно
    0.07
    anza
    0.06
    chio
    0.06
    è¶Ĭå°ij
    0.06
    ucs
    0.06
    ä¸ĭåIJĮ
    0.06
    Activations Density 0.285%

    No Known Activations