© 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. 10018
    Prev
    Next
    INDEX
    Explanations

    integer and float types

    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
    è¿ijå¹³
    -0.07
    lighet
    -0.07
     Colombo
    -0.07
    loe
    -0.07
    jš
    -0.07
    jte
    -0.07
    wen
    -0.07
    /providers
    -0.07
    ستÙĬ
    -0.07
    issan
    -0.07
    POSITIVE LOGITS
    egers
    0.10
    -val
    0.08
     valued
    0.07
    .TryParse
    0.07
    .Parse
    0.07
    ucks
    0.07
    lify
    0.07
    eger
    0.06
    asha
    0.06
    oller
    0.06
    Activations Density 0.114%

    No Known Activations