© 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. 39475
    Prev
    Next
    INDEX
    Explanations

    referring to above

    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
    _ET
    -0.07
    IBA
    -0.06
    /jav
    -0.06
    zor
    -0.06
    ģ
    -0.06
    OTS
    -0.06
    compile
    -0.06
    stva
    -0.06
    çŃīä¼łç»Ł
    -0.06
    ä¸įäºĨ
    -0.06
    POSITIVE LOGITS
     вÑĭÑĪе
    0.09
     above
    0.09
    ฯ
    0.08
    inch
    0.08
    ä¸Ĭè¿°
    0.08
    bove
    0.07
    utas
    0.07
    ç«ĭäºİ
    0.07
     Above
    0.07
    above
    0.07
    Activations Density 0.011%

    No Known Activations