© 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. 25473
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    ileo
    -0.08
    emper
    -0.08
    ạ
    -0.08
    åı¯æ¢¦
    -0.08
     Ejem
    -0.07
    oko
    -0.07
    çķĮ
    -0.07
    åŃIJãĤĴ
    -0.07
    "http
    -0.07
    Pers
    -0.07
    POSITIVE LOGITS
    ncer
    0.06
    WAY
    0.06
    ÏģÎŃ
    0.06
    thesize
    0.06
    inea
    0.06
    ways
    0.06
     concours
    0.06
    imulator
    0.06
    .linkedin
    0.06
    .
    0.06
    Activations Density 0.000%

    No Known Activations