© 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. 58483
    Prev
    Next
    INDEX
    Explanations

    continuation or quote markers

    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
     |:
    -0.09
    æł©æł©
    -0.09
    evenodd
    -0.09
    emball
    -0.08
     -**
    -0.08
     ("/
    -0.08
     "*
    -0.08
    )(*
    -0.08
     "\\
    -0.08
    ]("
    -0.08
    POSITIVE LOGITS
     (âĢ¦)
    0.19
     [âĢ¦
    0.18
     [âĢ¦]
    0.16
     [...]
    0.14
     âĢ¦
    0.13
    [,]
    0.13
    âĢ¦âĢ¦
    0.12
     [
    0.11
     (...)
    0.10
    [âĢ¦]
    0.10
    Activations Density 1.637%

    No Known Activations