© 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. 3921
    Prev
    Next
    INDEX
    Explanations

    codeblock closing punctuation

    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
    ouch
    -0.08
    ë§Ŀ
    -0.07
    _RESOLUTION
    -0.07
    üg
    -0.07
    JOR
    -0.07
    ills
    -0.07
     (("
    -0.07
    ä¸İåĪĽæĸ°
    -0.07
    ovin
    -0.06
    OOM
    -0.06
    POSITIVE LOGITS
    åĭ¤
    0.07
    ëijIJê³ł
    0.07
    emers
    0.07
    боÑİ
    0.06
    sel
    0.06
    ëĵłì§Ģ
    0.06
    ingas
    0.06
    ëĨĵê³ł
    0.06
    moid
    0.06
    okrat
    0.06
    Activations Density 0.012%

    No Known Activations