© 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. 64228
    Prev
    Next
    INDEX
    Explanations

    latex fractions

    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
    ä¸īåĪĨ
    -0.08
    çĭ¬
    -0.07
    irro
    -0.07
    ãĥģãĥ¥ãĥ¼
    -0.07
    èĬĴ
    -0.06
    ä¸Ń度
    -0.06
    èģĮ
    -0.06
    راد
    -0.06
    azzi
    -0.06
    apper
    -0.06
    POSITIVE LOGITS
    éĢļåĪĻ
    0.07
     بÙĬÙĨ
    0.07
    å¤ļä¹ħ
    0.07
    ä½ķæŶ
    0.07
    èĬ¹
    0.07
    ::-
    0.07
    éĻ¢æīĢ
    0.07
    éĽĨåħ¨
    0.07
    teggi
    0.06
    ±
    0.06
    Activations Density 0.006%

    No Known Activations