© 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. 50613
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions with exponents

    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
    ahun
    -0.08
    olar
    -0.07
    è®¤çľŁå¯¹å¾ħ
    -0.07
     Dud
    -0.07
     urn
    -0.06
    itone
    -0.06
    antor
    -0.06
    ãĤ³ãĤ¤ãĥ³
    -0.06
    uket
    -0.06
    鼷鼨
    -0.06
    POSITIVE LOGITS
    ç¦ģ
    0.08
     }</
    0.08
    istration
    0.08
    çļĵ
    0.07
    豫
    0.07
    ografie
    0.07
    èĬ®
    0.07
    wheel
    0.07
    =\"%
    0.07
    åŁºåĽł
    0.07
    Activations Density 0.069%

    No Known Activations