© 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. 61215
    Prev
    Next
    INDEX
    Explanations

    colon carcinoma

    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
    odon
    -0.07
     cÄĥn
    -0.07
    å¯Į
    -0.07
     isol
    -0.06
    Sharper
    -0.06
    ئات
    -0.06
    åħľ
    -0.06
    å¡ĺ
    -0.06
    Iterator
    -0.06
    ¦
    -0.06
    POSITIVE LOGITS
    éļĶ
    0.07
    ackers
    0.07
    stad
    0.07
     bè
    0.07
    jali
    0.07
    ä¸įçł´
    0.07
    jol
    0.07
    ungsver
    0.07
    _throw
    0.07
     Vila
    0.07
    Activations Density 0.037%

    No Known Activations