© 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. 21042
    Prev
    Next
    INDEX
    Explanations

    percentages

    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
    æĬ¤
    -0.08
    大å®Ŀ
    -0.07
    å£ķ
    -0.07
    诸
    -0.06
    ãĥ¬ãĤ¹ãĥĪ
    -0.06
     Dillon
    -0.06
     unr
    -0.06
    ÙĨدر
    -0.06
    大åѦæİĴåIJį
    -0.06
    brug
    -0.06
    POSITIVE LOGITS
     percentage
    0.23
    çĻ¾åĪĨæ¯Ķ
    0.21
    çĻ¾åĪĨä¹ĭ
    0.21
    _percentage
    0.20
    percentage
    0.20
    åįłæ¯Ķ
    0.20
     Percentage
    0.20
     percentages
    0.19
     percent
    0.19
    Percentage
    0.19
    Activations Density 0.420%

    No Known Activations