© 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. 2409
    Prev
    Next
    INDEX
    Explanations

    design, spending, process, Ash, Club, Pediatric

    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
    Ø©
    -0.32
    er
    -0.25
    ä½Ĩä¸įéĻIJäºİ
    -0.21
    ÏĤ
    -0.20
    erÃŃa
    -0.15
    ive
    -0.15
    ìĦľëĬĶ
    -0.15
    ness
    -0.14
    ÙħÙĥاÙĨ
    -0.14
    vironment
    -0.14
    POSITIVE LOGITS
    ers
    0.16
    raries
    0.16
    zelfde
    0.15
    д
    0.12
    an
    0.12
    м
    0.11
    ãĥ³
    0.11
    ally
    0.11
    ìį¨
    0.11
    itional
    0.11
    Activations Density 4.380%

    No Known Activations