© 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. 19519
    Prev
    Next
    INDEX
    Explanations

    code block punctuation

    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
    ixmap
    -0.10
     Pian
    -0.09
    ¶ļ
    -0.09
    irat
    -0.09
    ulton
    -0.08
     Conserv
    -0.08
    .prototype
    -0.08
    inaldo
    -0.08
    çľ¯çľ¯
    -0.08
    cad
    -0.08
    POSITIVE LOGITS
    Tro
    0.07
    omen
    0.06
     Tro
    0.06
    纵
    0.06
    om
    0.06
    Lo
    0.05
     omit
    0.05
    ↵
    0.05
     Gle
    0.05
    '
    0.05
    Activations Density 0.162%

    No Known Activations