© 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. 3247
    Prev
    Next
    INDEX
    Explanations

    code programming keywords

    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
    Âł
    -0.11
    nok
    -0.07
    -0.07
    تÙĬ
    -0.07
    ³³³
    -0.06
    åĽ¾æºIJ
    -0.06
     to
    -0.06
    åĪ°ä¸Ģèµ·
    -0.06
    å½ĵæŶ
    -0.06
    γο
    -0.06
    POSITIVE LOGITS
    .targets
    0.08
    æ±
    0.08
    aleigh
    0.07
    çļĦ
    0.07
    gada
    0.07
    [email
    0.07
    lean
    0.07
    åĪ¸
    0.07
    wrapper
    0.07
     Rosenstein
    0.07
    Activations Density 0.446%

    No Known Activations