© 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. 11077
    Prev
    Next
    INDEX
    Explanations

    true or pass

    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
    alth
    -0.07
    æļ¨
    -0.07
    å®ģ
    -0.07
    aten
    -0.06
     OR
    -0.06
    ä¼ģ
    -0.06
    acar
    -0.06
    太å¤ļ
    -0.06
    è°ĥ
    -0.06
    agal
    -0.06
    POSITIVE LOGITS
     while
    0.10
    while
    0.10
    èĢĮèĩªå·±
    0.10
    èĢĮåħ¶
    0.09
    èĢĮ对
    0.09
     tandis
    0.09
    èĢĮéĻį
    0.09
     whilst
    0.09
    èĢĮçĶŁ
    0.09
     sedangkan
    0.09
    Activations Density 0.193%

    No Known Activations