© 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. 42808
    Prev
    Next
    INDEX
    Explanations

    Greek letters and variables

    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
    eland
    -0.08
    ä¸ĭå±±
    -0.07
     Pars
    -0.07
    enam
    -0.07
    æĸ°éĹ»ç½ij
    -0.07
    ç½ijåıĭè¯Ħ论
    -0.07
    ãģ®ãĤ¹
    -0.07
    ãģ£ãģį
    -0.07
    tral
    -0.07
    anel
    -0.06
    POSITIVE LOGITS
    orris
    0.07
    idge
    0.07
    读å®Į
    0.07
    éĿ¢å¯¹
    0.06
    assy
    0.06
    ANTE
    0.06
    å©Ĩ
    0.06
    .gpu
    0.06
    ợ
    0.06
    ante
    0.06
    Activations Density 0.004%

    No Known Activations