© 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. 2286
    Prev
    Next
    INDEX
    Explanations

    .com set

    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
    åĨįä»İ
    -0.07
    γγελ
    -0.07
    æĪŁ
    -0.07
    åĨįæİ¥
    -0.06
     brow
    -0.06
    æ¸
    -0.06
    emberg
    -0.06
    èĤĨ
    -0.06
    æĪĴ
    -0.06
    åĨįè¿Ľè¡Į
    -0.06
    POSITIVE LOGITS
    jem
    0.08
    åIJĮæł·çļĦ
    0.08
    uten
    0.07
    STE
    0.07
    æĢ§äº¤
    0.07
    inda
    0.07
    oplan
    0.07
    ắp
    0.07
    es
    0.07
    lob
    0.07
    Activations Density 0.233%

    No Known Activations