© 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. 22538
    Prev
    Next
    INDEX
    Explanations

    compare, find, examined, experiments

    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
    ä¸įå¼Ģ
    -0.07
    èĢĮè¿Ļç§į
    -0.07
    æĺ¯å¦ĤæѤ
    -0.07
    ëĿ½
    -0.07
    çļĦéĤ£ç§į
    -0.07
    ellis
    -0.06
     brand
    -0.06
    åı¯ä»¥èĩªå·±
    -0.06
    å½ĵçĦ¶
    -0.06
    accio
    -0.06
    POSITIVE LOGITS
    "":
    0.10
     ?:
    0.08
    }):
    0.07
    mén
    0.07
     **:
    0.07
    %%%%
    0.07
    )':
    0.07
    ardown
    0.07
    éĢĻå°į
    0.07
    è¿Ļ对
    0.07
    Activations Density 0.007%

    No Known Activations