© 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. 42455
    Prev
    Next
    INDEX
    Explanations

    punctuation and numbers

    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
    xil
    -0.08
    strup
    -0.07
    æīĢ幸
    -0.07
    issan
    -0.07
    .dispose
    -0.07
    amac
    -0.07
    æŃ»ä¸į
    -0.07
    arde
    -0.07
    inox
    -0.06
    ÙĪÙĬÙĩ
    -0.06
    POSITIVE LOGITS
    èµı
    0.08
    è³ŀ
    0.08
    éĹ»
    0.07
    æĪijåıªæĥ³
    0.07
     conse
    0.07
    .defaults
    0.07
    vall
    0.07
    IMA
    0.07
    æ´Ľæĸ¯
    0.07
    æĸ°
    0.07
    Activations Density 0.027%

    No Known Activations