© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 48814
    Prev
    Next
    INDEX
    Explanations

    quantifiable measures

    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
    inker
    -0.08
    _DOM
    -0.07
    okol
    -0.06
    ipse
    -0.06
    ags
    -0.06
    occhi
    -0.06
    èĩªæĿ¥
    -0.06
    ä¸įæĸŃ丰å¯Į
    -0.06
    à¸ĸม
    -0.06
    ioneer
    -0.06
    POSITIVE LOGITS
     necessary
    0.15
     needed
    0.15
    å¿ħè¦ģçļĦ
    0.14
     Needed
    0.14
    needed
    0.14
    å¿ħè¦ģ
    0.13
    necessary
    0.13
    å¿ħè¦ģæŶ
    0.13
     Necessary
    0.13
     enough
    0.12
    Activations Density 0.298%

    No Known Activations