© 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. 12502
    Prev
    Next
    INDEX
    Explanations

    optional

    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
    æĪĸèĢħ说
    -0.07
    èĩ³å°ijæľī
    -0.07
     Chinh
    -0.07
    èī¯ä¹ħ
    -0.07
     Likely
    -0.07
    èµ·çłģ
    -0.07
    ä¸į说
    -0.07
    åıĹ访
    -0.07
    ä¸Ķåħ·æľī
    -0.07
     likely
    -0.06
    POSITIVE LOGITS
     additional
    0.10
    (optional
    0.09
     optionally
    0.09
     dodatkowo
    0.09
     uncomment
    0.09
    additional
    0.09
     optional
    0.09
     additionally
    0.09
     дополниÑĤелÑĮно
    0.09
    é¢Ŀå¤ĸçļĦ
    0.08
    Activations Density 0.213%

    No Known Activations