© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 2499
    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
    ÃŃna
    -0.07
    ym
    -0.06
    jaar
    -0.06
    æ¯ıéļĶ
    -0.06
    èµ·äºĨ
    -0.06
    ë²Į
    -0.06
    èħ¾ç©º
    -0.06
    .intent
    -0.06
    ite
    -0.06
    åĩºåħ·
    -0.06
    POSITIVE LOGITS
    ulli
    0.09
     respect
    0.08
    idden
    0.08
    agaan
    0.08
    éĿĴè¡£
    0.08
    usin
    0.08
    TemplateName
    0.08
    å°Ĭéĩį
    0.08
    lei
    0.07
    åıªæľīèĩªå·±
    0.07
    Activations Density 0.000%

    No Known Activations