© 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. 10840
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions

    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
    espo
    -0.07
    UMB
    -0.07
    è¡ħ
    -0.07
    umb
    -0.07
    aventure
    -0.07
    peen
    -0.07
    nea
    -0.06
    mith
    -0.06
    沿
    -0.06
     Gregg
    -0.06
    POSITIVE LOGITS
    anha
    0.07
    odi
    0.07
    èī²åĪĹ
    0.07
    lement
    0.07
     Bund
    0.07
     Dres
    0.07
    ä¸īä¼ļ
    0.07
    _HAVE
    0.07
    chsel
    0.07
    _POL
    0.06
    Activations Density 0.007%

    No Known Activations