© 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. 57863
    Prev
    Next
    INDEX
    Explanations

    Bill Peyton

    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
    åī§
    -0.07
    egov
    -0.07
    ukul
    -0.07
    å®ĩå®ĻçļĦ
    -0.06
    èĬĿ
    -0.06
     perfected
    -0.06
    ÄĥÈĻ
    -0.06
    æĿ¥æºIJç½ij绾
    -0.06
    etak
    -0.06
     perfect
    -0.06
    POSITIVE LOGITS
    ä¿Ŀè¯ģåħ¶
    0.08
     its
    0.08
    å¾Ĺåħ¶
    0.08
    为åħ¶
    0.08
    åıĸæ¶Īåħ¶
    0.08
    对åħ¶
    0.07
    åħ¶ä¸İ
    0.07
    accio
    0.07
    åħ¶å¯¹
    0.07
    Writable
    0.07
    Activations Density 0.022%

    No Known Activations