© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 7286
    Prev
    Next
    INDEX
    Explanations

    code element syntax

    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
    åĴĮéĩįçĤ¹
    -0.07
    æīĭä¸ĬçļĦ
    -0.07
    ym
    -0.07
    mani
    -0.07
    yn
    -0.07
     incond
    -0.07
    éĹ®é¢ĺåĪĨæŀIJ
    -0.07
     deltaY
    -0.07
    .Mask
    -0.06
    orsch
    -0.06
    POSITIVE LOGITS
    çīĽ
    0.07
    geg
    0.07
    ç±»åĪ«
    0.07
    hte
    0.07
    inj
    0.06
    oroz
    0.06
    CATEGORY
    0.06
    istri
    0.06
    öld
    0.06
     classifications
    0.06
    Activations Density 0.107%

    No Known Activations