© 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. 8489
    Prev
    Next
    INDEX
    Explanations

    case citations and journal articles

    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
    NEG
    -0.08
    ayu
    -0.08
     opa
    -0.07
    scoped
    -0.07
    estre
    -0.07
    bine
    -0.07
    å®ŀè¯Ŀ
    -0.07
    秸
    -0.07
    riere
    -0.07
    uff
    -0.07
    POSITIVE LOGITS
    obo
    0.07
    ×ķ×Ĵ
    0.06
    æī
    0.06
     Copyright
    0.06
    -dev
    0.06
    ites
    0.06
    æİ
    0.06
    æĺ¯ä¸Ģç§į常è§ģçļĦ
    0.06
    ä½ĵè£ģ
    0.06
    ợi
    0.06
    Activations Density 0.111%

    No Known Activations