© 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. 18961
    Prev
    Next
    INDEX
    Explanations

    question words

    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
    æľĢæĸ°æĸĩç«ł
    -0.07
    éħĶ
    -0.07
    ehm
    -0.06
     Adapt
    -0.06
    åħ¬åı¸ä»ĭç»į
    -0.06
     Ø¢ÙħدÙĩ
    -0.06
     repro
    -0.06
    æĽ´éĩįè¦ģçļĦæĺ¯
    -0.06
    oader
    -0.06
     fasc
    -0.06
    POSITIVE LOGITS
    大ä¸ĸçķĮ
    0.08
    Sentence
    0.08
    utters
    0.08
    èľ¡
    0.08
    ASF
    0.08
    ạp
    0.07
    swire
    0.07
     خز
    0.07
    ynet
    0.07
    çļĦ亲
    0.07
    Activations Density 0.403%

    No Known Activations