© 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. 24412
    Prev
    Next
    INDEX
    Explanations

    live:

    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¸įåİĮ
    -0.08
    _dispatch
    -0.07
    åijĬè¯īä»ĸ们
    -0.07
    ablanca
    -0.07
    _published
    -0.07
    ighth
    -0.07
    éĢı
    -0.06
     desp
    -0.06
     nad
    -0.06
    对大家
    -0.06
    POSITIVE LOGITS
     Gund
    0.08
    积æŀģåıĤåĬł
    0.08
    çĭ¬ç«ĭçļĦ
    0.07
    åģİ
    0.07
    ews
    0.07
    agu
    0.07
    å¦Ĥæŀľåı¯ä»¥
    0.07
    _submission
    0.07
    alyzed
    0.07
    èĩªæ²»
    0.07
    Activations Density 0.244%

    No Known Activations