© 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. 41985
    Prev
    Next
    INDEX
    Explanations

    python imports

    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
     inf
    -0.08
    voer
    -0.07
    iant
    -0.07
    ÙĬÙĨت
    -0.07
    обен
    -0.06
    ultipart
    -0.06
    £¼
    -0.06
    bben
    -0.06
    utant
    -0.06
    çĶ¨è½¦
    -0.06
    POSITIVE LOGITS
    anny
    0.07
    serde
    0.07
    azo
    0.07
    ulp
    0.07
    annie
    0.07
    Readable
    0.07
    .flip
    0.07
    羣æŃ£æĦıä¹īä¸ĬçļĦ
    0.07
    éģŀ
    0.07
    ç»į
    0.07
    Activations Density 0.013%

    No Known Activations