© 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. 28320
    Prev
    Next
    INDEX
    Explanations

    dates before texts

    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
     Sands
    -0.07
    atória
    -0.07
    为è¾ħ
    -0.06
    计ç®Ĺæľºç§ijåѦ
    -0.06
    atin
    -0.06
    više
    -0.06
    ç¾İå·¥
    -0.06
    æĬĺ
    -0.06
    anford
    -0.06
    ãi
    -0.06
    POSITIVE LOGITS
    äºĨäºĭ
    0.08
    åı£æ°´
    0.07
    IBLE
    0.07
    说ä¸įåĩºçļĦ
    0.07
    |--
    0.07
    agal
    0.07
    èıľè°±
    0.07
    éĨ
    0.07
    åĴĮçĶ°
    0.07
    etype
    0.07
    Activations Density 0.009%

    No Known Activations