© 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. 26743
    Prev
    Next
    INDEX
    Explanations

    conservation programs

    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
    aven
    -0.07
    bem
    -0.07
    غÙĨ
    -0.06
    amore
    -0.06
    oth
    -0.06
    chini
    -0.06
    é¢ľåħŃ
    -0.06
    amins
    -0.06
    è·Łåįķ
    -0.06
    麦å½ĵ
    -0.06
    POSITIVE LOGITS
    odox
    0.09
    erre
    0.07
    &page
    0.07
    à¸ļุรี
    0.07
     nutric
    0.07
    _expired
    0.07
    nger
    0.06
    ä¿Ŀè¯ģåħ¶
    0.06
     Recap
    0.06
    еÑģÑĤа
    0.06
    Activations Density 0.466%

    No Known Activations