© 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. 62150
    Prev
    Next
    INDEX
    Explanations

    bisphosphonate, ageing, mediated, year, CTLA, .txt, colour, specific, year, protein

    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
    ers
    -0.16
    raries
    -0.15
    zelfde
    -0.15
    д
    -0.13
    ìį¨
    -0.12
    ally
    -0.11
    ãĥ¥
    -0.11
    an
    -0.11
    itional
    -0.11
    rastructure
    -0.11
    POSITIVE LOGITS
    Ø©
    0.30
    er
    0.25
    ä½Ĩä¸įéĻIJäºİ
    0.22
    ÏĤ
    0.19
    ive
    0.15
    erÃŃa
    0.14
    ìĦľëĬĶ
    0.14
    vironment
    0.14
    ÙħÙĥاÙĨ
    0.13
    ìĸ´
    0.13
    Activations Density 6.592%

    No Known Activations