© 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. 18305
    Prev
    Next
    INDEX
    Explanations

    evaluation grades

    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
    atika
    -0.08
     Powered
    -0.08
    æ¶Ī
    -0.08
    anson
    -0.07
     Fry
    -0.07
     Horr
    -0.07
     Tý
    -0.07
    æ¯ıæĹ¥ä¸Ģç»ĥ
    -0.07
     تÙĤرÙĬب
    -0.07
    powered
    -0.07
    POSITIVE LOGITS
    ä¸Ģæ¡£
    0.10
     (>
    0.07
    äºĨçļĦ
    0.07
    轩
    0.06
    åıĬ以ä¸Ĭ
    0.06
     borders
    0.06
     voire
    0.06
    irable
    0.06
    以ä¸ĬçļĦ
    0.06
    åıĤèĢĥä»·åĢ¼
    0.06
    Activations Density 0.053%

    No Known Activations