© 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. 19041
    Prev
    Next
    INDEX
    Explanations

    chemical formulas

    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
    å¥½ä¸ľè¥¿
    -0.07
    anyl
    -0.07
    HING
    -0.07
    æĿ¥èĩªç½ij绾
    -0.07
    args
    -0.07
    IZER
    -0.07
    ä¸Ģäºĭ
    -0.06
    éĹ®é¢ĺçļĦèĥ½åĬĽ
    -0.06
    çĪ·
    -0.06
    uhkan
    -0.06
    POSITIVE LOGITS
    æ¿®
    0.07
    ario
    0.07
    禺
    0.07
    æ±ķ
    0.06
    çģĮ
    0.06
    _MEDIUM
    0.06
    .monitor
    0.06
    åŃļ
    0.06
    conv
    0.06
    .DataTable
    0.06
    Activations Density 0.005%

    No Known Activations