© 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. 27325
    Prev
    Next
    INDEX
    Explanations

    extracting values and converting data 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
    ÏħÏĩ
    -0.07
     обаÑĩ
    -0.07
    ibas
    -0.07
    éĤģ
    -0.07
    aunch
    -0.07
    ivor
    -0.07
    èĢĮä»Ĭ
    -0.07
    _putchar
    -0.06
    bus
    -0.06
    θα
    -0.06
    POSITIVE LOGITS
    Parsed
    0.10
     converts
    0.08
    convert
    0.08
     convert
    0.08
     canon
    0.08
     conversion
    0.08
    .convert
    0.08
    FromString
    0.07
     unpack
    0.07
    å®ŀå¤Ħ
    0.07
    Activations Density 0.049%

    No Known Activations