© 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. 60467
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions or variable assignments

    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
    说æĺİ
    -0.07
    λιο
    -0.07
     disg
    -0.07
    ãĤ»ãĥ³
    -0.07
    гл
    -0.07
    itari
    -0.07
    udo
    -0.06
    umen
    -0.06
    gress
    -0.06
    ç»ı常æĢ§
    -0.06
    POSITIVE LOGITS
    tage
    0.08
    iby
    0.08
    presa
    0.08
    æľªçĦ¶
    0.08
    addError
    0.07
    _numer
    0.07
    arde
    0.07
    /sites
    0.07
    ži
    0.07
    æ¡¥åĮº
    0.07
    Activations Density 0.005%

    No Known Activations