© 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. 39399
    Prev
    Next
    INDEX
    Explanations

    percentages and ratios

    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
    ноп
    -0.09
    å¸Ĥæĸ°
    -0.08
    å¸Ĥå±Ģ
    -0.07
    ievo
    -0.07
    ustru
    -0.07
    -Smith
    -0.07
     اشت
    -0.07
    attore
    -0.07
    áŀľ
    -0.07
    engang
    -0.06
    POSITIVE LOGITS
    以太
    0.08
     bath
    0.08
    äºķ
    0.07
    çĻ¾åĪĨä¹ĭ
    0.07
    çĽ¯
    0.07
     ratios
    0.07
    ä¸ĩåĪĨ
    0.07
     fraction
    0.07
    éĩij鸡
    0.07
    argin
    0.07
    Activations Density 0.012%

    No Known Activations