© 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. 51531
    Prev
    Next
    INDEX
    Explanations

    Adam Curry, Gary Craig, H. P. Lovecraft

    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
    éĢĹ
    -0.09
    æ·
    -0.08
    ambah
    -0.08
    æı©
    -0.07
    اÙĨÙĩ
    -0.07
    ä¹į
    -0.07
    пеÑĢа
    -0.07
    åĪĩå®ŀå¢ŀ强
    -0.07
     tarihi
    -0.07
    tober
    -0.07
    POSITIVE LOGITS
    为代表çļĦ
    0.09
    åıĬåħ¶
    0.09
    为代表
    0.09
     spear
    0.09
    åĢ¡å¯¼
    0.08
    enberg
    0.08
    .define
    0.08
    çļĦä¸Ģç³»åĪĹ
    0.08
    为é¦ĸçļĦ
    0.08
     advocate
    0.07
    Activations Density 0.106%

    No Known Activations