© 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. 34729
    Prev
    Next
    INDEX
    Explanations

    metric tensor $g_{ij}$

    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
    sä
    -0.08
    acken
    -0.07
     vX
    -0.07
    /exp
    -0.07
    kov
    -0.07
    åıijå±ķ壮大
    -0.07
     pror
    -0.07
    vens
    -0.07
    rex
    -0.06
    ê¸°ë¡ľ
    -0.06
    POSITIVE LOGITS
    çī§
    0.07
    鸳
    0.07
    ļ
    0.07
    ãģ©ãģĵãĤį
    0.07
    鸳鸯
    0.07
    å¼¹
    0.07
    imbra
    0.07
    ÏĢλα
    0.07
    å½ĵä¹ĭ
    0.07
    olan
    0.06
    Activations Density 0.001%

    No Known Activations