© 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. 39571
    Prev
    Next
    INDEX
    Explanations

    size and measurements

    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
    å®Ī
    -0.07
    âĢ¢
    -0.06
    ptic
    -0.06
    Ïģγ
    -0.06
     Cum
    -0.06
    æ°ı
    -0.06
    äºĭçī©
    -0.06
    .edu
    -0.06
    毯
    -0.06
    课ä½Ļ
    -0.05
    POSITIVE LOGITS
    /story
    0.08
    æĪĸ以ä¸Ĭ
    0.08
    wiet
    0.08
    beauf
    0.08
    ysize
    0.08
    éĤ£å¹´
    0.07
    ä¸½å¨ľ
    0.07
     Conforme
    0.07
    gris
    0.07
    lias
    0.07
    Activations Density 0.026%

    No Known Activations