© 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. 8610
    Prev
    Next
    INDEX
    Explanations

    dreaming and dreams

    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
    ities
    -0.09
    иÑģк
    -0.08
    ity
    -0.08
    atest
    -0.08
    å¾·éŁ³
    -0.08
    estro
    -0.07
    ocu
    -0.07
    glieder
    -0.07
    ç²Ľ
    -0.07
    æĸĩåĵ²
    -0.07
    POSITIVE LOGITS
    æĪIJ羣
    0.13
    çł´çģŃ
    0.11
    å¯IJ
    0.10
    ä¸İçİ°å®ŀ
    0.10
    cape
    0.09
    licherweise
    0.09
    ĥĿ
    0.08
    hafte
    0.08
    rial
    0.08
    çļĦå®ŀçİ°
    0.08
    Activations Density 0.022%

    No Known Activations