© 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. 62898
    Prev
    Next
    INDEX
    Explanations

    image captions or labels

    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
     cry
    -0.07
    tsy
    -0.07
    of
    -0.07
    zog
    -0.07
    å¼ĤåĽ½
    -0.06
    istributed
    -0.06
    å»ĵ
    -0.06
    饲
    -0.06
    å¤įåIJĪ
    -0.06
     themselves
    -0.06
    POSITIVE LOGITS
    åij»
    0.07
    æµ·åĮº
    0.07
    elyn
    0.07
    ä¸įå®ļ
    0.07
    uar
    0.07
    orns
    0.07
    ager
    0.07
    erna
    0.07
    çĻ¾åĪĨ
    0.07
    AdminController
    0.06
    Activations Density 0.002%

    No Known Activations