© 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. 62208
    Prev
    Next
    INDEX
    Explanations

    questions and answers

    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
    <|box_end|>
    -0.08
    .Names
    -0.08
    asl
    -0.07
    èݹ
    -0.07
    ivel
    -0.07
    	names
    -0.07
    æįĮ
    -0.07
    ä¸Ĭ马
    -0.07
    äºĨäºĽ
    -0.07
    SEE
    -0.07
    POSITIVE LOGITS
    owi
    0.07
    pell
    0.07
    alsy
    0.07
    icha
    0.06
    æ°Ķ象åı°
    0.06
    ace
    0.06
    åħ¼
    0.06
     Spike
    0.06
     reck
    0.06
    ema
    0.06
    Activations Density 0.003%

    No Known Activations