© 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. 13449
    Prev
    Next
    INDEX
    Explanations

    either side or sandwiched

    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
     newInstance
    -0.07
    Õ¹
    -0.07
     Bur
    -0.07
    Bur
    -0.07
    åĮºåĪ«
    -0.07
    é¢Ĩ导å°ıç»ĦåĬŀåħ¬å®¤
    -0.07
    reja
    -0.07
    allis
    -0.07
    theon
    -0.06
    enga
    -0.06
    POSITIVE LOGITS
    ä¸Ĭä¸ĭ
    0.17
    两端
    0.17
    å·¦åı³
    0.16
    åīįåIJİ
    0.16
    åīįåIJİçļĦ
    0.15
    两侧
    0.15
    两头
    0.14
    åīįå¾Į
    0.14
    çĤ¹å·¦åı³
    0.13
    两边
    0.13
    Activations Density 0.141%

    No Known Activations