© 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. 29356
    Prev
    Next
    INDEX
    Explanations

    after "cod" or "Lewis", "heroes", "men", "lives", "were", "lights"

    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
    enties
    -0.08
    éĢIJ级
    -0.08
    æµ®
    -0.07
    ç²Ĺæļ´
    -0.07
    åĬŀåħ¬å®¤éĩĮ
    -0.07
    ache
    -0.07
     tort
    -0.07
    rogen
    -0.06
    æĸ¹æĸ¹éĿ¢
    -0.06
    å¾ģç¨ĭ
    -0.06
    POSITIVE LOGITS
    itest
    0.07
     locus
    0.07
     ÙĤاب
    0.07
    acute
    0.07
    æ®ī
    0.07
     dependable
    0.07
    gemeinschaft
    0.07
    è§ĨçĤ¹
    0.07
    åĪ©å®³
    0.07
    äll
    0.07
    Activations Density 0.002%

    No Known Activations