© 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. 42107
    Prev
    Next
    INDEX
    Explanations

    size and length of data

    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
    rero
    -0.08
    çĽ¸ä¼¼æĸĩçĮ®
    -0.08
    ATHER
    -0.08
    egno
    -0.08
    refix
    -0.08
    onyme
    -0.08
    Gatt
    -0.08
    satz
    -0.08
    .setLevel
    -0.08
    ryw
    -0.08
    POSITIVE LOGITS
    è¡Įæķ°
    0.08
     length
    0.07
    æķ°éĩıåĴĮ
    0.07
     counted
    0.07
     counting
    0.07
    ä¸įç®Ĺ
    0.06
    äºĨå¤ļå°ij
    0.06
    ä¸Ģè¡Į
    0.06
     spaces
    0.06
    æľīå¤ļå°ij
    0.06
    Activations Density 0.021%

    No Known Activations