© 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. 8531
    Prev
    Next
    INDEX
    Explanations

    filepaths or variable names

    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
    inv
    -0.07
    Inv
    -0.07
    å½ĵãģŁãĤĬ
    -0.07
    .inv
    -0.07
    urement
    -0.07
    פר
    -0.06
     Inv
    -0.06
    à¬ĸ
    -0.06
    ién
    -0.06
    geme
    -0.06
    POSITIVE LOGITS
    å½Ĵå±ŀäºİä¸Ĭå¸Ĥåħ¬åı¸èĤ¡ä¸ľçļĦ
    0.07
    격ìĿĦ
    0.07
    ``,
    0.07
    ³³³³
    0.07
    lickr
    0.06
    ears
    0.06
    bac
    0.06
    çļĦåij¢
    0.06
    бÑĢи
    0.06
    edList
    0.06
    Activations Density 0.079%

    No Known Activations