© 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. 63746
    Prev
    Next
    INDEX
    Explanations

    continue a thought or sentence

    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
     admir
    -0.08
    &view
    -0.07
    ë¡Ģ
    -0.07
    ç¯ĩä¸ī
    -0.07
    æĪĸ许æĺ¯
    -0.07
     figur
    -0.06
    å·¥ä½ľé¢Ĩ导å°ıç»Ħ
    -0.06
    ç¼ļ
    -0.06
    comic
    -0.06
     Fid
    -0.06
    POSITIVE LOGITS
    ÑĢил
    0.08
    axe
    0.07
    ç¡ķ
    0.07
    Injected
    0.07
    碩
    0.07
    лга
    0.07
    ãħĩ
    0.07
    ằn
    0.07
    enerate
    0.06
    ctal
    0.06
    Activations Density 0.242%

    No Known Activations