© 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. 41314
    Prev
    Next
    INDEX
    Explanations

    reverse transcription

    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
     Gas
    -0.07
     Newton
    -0.07
    天ä¸ĭ第ä¸Ģ
    -0.07
    èī¯
    -0.07
     fract
    -0.07
     gas
    -0.07
    che
    -0.07
    Insensitive
    -0.07
    burger
    -0.06
    å´ĩ
    -0.06
    POSITIVE LOGITS
    convert
    0.10
     converting
    0.10
     Convert
    0.10
     convert
    0.09
     Converts
    0.09
    转åĮĸçļĦ
    0.09
     conversions
    0.09
    Convert
    0.08
     converts
    0.08
    conversion
    0.08
    Activations Density 0.021%

    No Known Activations