© 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. 47577
    Prev
    Next
    INDEX
    Explanations

    operators, algebra, license, bracket

    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
    éĴµ
    -0.07
    HEN
    -0.07
     liá»ĩu
    -0.07
    _mE
    -0.07
    .rstrip
    -0.07
    çĽ¸äº²
    -0.07
    panse
    -0.06
    ļĮ
    -0.06
    osas
    -0.06
     sacrificed
    -0.06
    POSITIVE LOGITS
    -operator
    0.08
    强弱
    0.08
     Operators
    0.08
     Operator
    0.07
    碾
    0.07
     Maestro
    0.07
    Operator
    0.07
     operator
    0.07
    è¾Ī
    0.07
     operators
    0.07
    Activations Density 0.001%

    No Known Activations