© 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. 25751
    Prev
    Next
    INDEX
    Explanations

    research and innovation

    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
    chner
    -0.08
    cak
    -0.08
    åħ¶èº«
    -0.07
     muka
    -0.07
     EDUCA
    -0.07
    deo
    -0.07
    æĿĥåĪ©ä¹īåĬ¡
    -0.07
     antrop
    -0.07
    ofer
    -0.07
    幸ç¦ıçĶŁæ´»
    -0.07
    POSITIVE LOGITS
    éĻ¢å£«
    0.12
    /engine
    0.11
     scientists
    0.10
    æĶ»åħ³
    0.10
    ä¸İåĪĽæĸ°
    0.10
    ç§ijåŃ¦å®¶
    0.10
    åĴĮåĪĽæĸ°
    0.09
     Intellectual
    0.09
     scientist
    0.09
     Scientists
    0.09
    Activations Density 0.146%

    No Known Activations