© 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. 43049
    Prev
    Next
    INDEX
    Explanations

    -proof

    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
    äºĽ
    -0.08
    hir
    -0.07
    åĿļ
    -0.07
    acht
    -0.06
    aw
    -0.06
    ben
    -0.06
    <<<
    -0.05
    æµĩ
    -0.05
    aurus
    -0.05
    ar
    -0.05
    POSITIVE LOGITS
    åĴ²
    0.08
    天å®ĩ
    0.08
    cid
    0.08
    ç§ĭ鼨
    0.08
    usat
    0.07
    utore
    0.07
    æķ¬
    0.07
    ugi
    0.07
    æŁ»
    0.07
    _dn
    0.07
    Activations Density 0.150%

    No Known Activations