© 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. 25194
    Prev
    Next
    INDEX
    Explanations

    positive outcomes or evaluations

    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
    ce
    -0.07
    ä¸ĢæĹł
    -0.06
     ,
    -0.06
    èģĶ
    -0.06
     appropriately
    -0.06
     appropriate
    -0.06
     pri
    -0.06
     app
    -0.06
    -
    -0.06
    lee
    -0.06
    POSITIVE LOGITS
    urette
    0.10
    ç¬Ļ
    0.08
    çŃīçĿĢä½ł
    0.08
    ulier
    0.08
    æĤ¨å·²ç»ı
    0.08
    kok
    0.08
    amac
    0.08
    olars
    0.08
    inander
    0.08
    smouth
    0.08
    Activations Density 0.001%

    No Known Activations