© 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. 63877
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions with variables

    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
     either
    -0.07
     ,
    -0.07
    rib
    -0.07
    iral
    -0.06
    ...
    -0.06
    irable
    -0.06
    iste
    -0.06
     —
    -0.06
     Universal
    -0.06
    å¦Ĥä¸ĭ
    -0.06
    POSITIVE LOGITS
    ãĥĩãĤ£ãĤª
    0.08
    aic
    0.08
    ijo
    0.08
     оконÑĩаÑĤелÑĮно
    0.08
    өл
    0.08
    =”
    0.07
    accio
    0.07
    überg
    0.07
    cios
    0.07
    kob
    0.07
    Activations Density 0.004%

    No Known Activations