© 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. 22087
    Prev
    Next
    INDEX
    Explanations

    effective dates and transitions

    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
    年建éĢł
    -0.08
    _RCC
    -0.08
    å½ĴæĿ¥
    -0.08
    /MPL
    -0.07
    GED
    -0.07
    bior
    -0.07
     kÃŃn
    -0.07
    Repeated
    -0.07
    ä¼ģæŁ¥æŁ¥
    -0.07
    ĥģ
    -0.07
    POSITIVE LOGITS
    çĶŁæķĪ
    0.13
    è¿ĩ渡
    0.08
     pending
    0.08
    effective
    0.08
     implementation
    0.08
     transition
    0.08
     effective
    0.08
     date
    0.08
    失æķĪ
    0.08
     grandfather
    0.07
    Activations Density 0.262%

    No Known Activations