© 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. 63885
    Prev
    Next
    INDEX
    Explanations

    code blocks and structure

    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
    .aspx
    -0.07
    ÙĬÙĩ
    -0.07
    ingly
    -0.07
    .net
    -0.06
    http
    -0.06
    çĿ¿
    -0.06
     minus
    -0.06
    è¶Ł
    -0.06
    optgroup
    -0.06
     Loves
    -0.06
    POSITIVE LOGITS
    ontos
    0.08
    llib
    0.07
    atih
    0.07
    BITS
    0.07
    æĽ´æĸ°äºİ
    0.07
    æĭĴ
    0.07
    elit
    0.07
    itier
    0.07
    oppable
    0.07
    izzle
    0.07
    Activations Density 0.001%

    No Known Activations