© 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. 8873
    Prev
    Next
    INDEX
    Explanations

    distance measurements

    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
    enton
    -0.07
    ç»ĵæŀĦåĮĸ
    -0.07
     trickle
    -0.07
    thouse
    -0.07
    çĻ¾
    -0.07
    åıªåī©ä¸ĭ
    -0.07
     Rahman
    -0.07
    æ¡Ĩ
    -0.06
     garn
    -0.06
    æľºèĥ½
    -0.06
    POSITIVE LOGITS
     distance
    0.08
    Distance
    0.08
    è·Ŀ离
    0.07
     distances
    0.07
    locker
    0.07
    å¤ĸ侧
    0.07
    عار
    0.07
     interd
    0.07
    èĴĤæĸ¯
    0.07
    _distance
    0.07
    Activations Density 0.003%

    No Known Activations