© 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. 64295
    Prev
    Next
    INDEX
    Explanations

    code block terminators

    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
    rakt
    -0.09
    ï¸ı
    -0.09
    theless
    -0.09
    erer
    -0.09
    ĥĿ
    -0.09
    /manage
    -0.08
    itious
    -0.08
    .xhtml
    -0.08
    .Keys
    -0.08
     setFrame
    -0.08
    POSITIVE LOGITS
     lus
    0.06
    æıIJ
    0.06
     else
    0.06
    人éģĵ
    0.06
    ms
    0.06
    usz
    0.06
    æĮĩ
    0.06
     absolut
    0.06
    telef
    0.06
    æij©
    0.05
    Activations Density 0.003%

    No Known Activations