© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 20329
    Prev
    Next
    INDEX
    Explanations

    `const` or `get` keywords followed by `;` or `{`

    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
     заÑģлÑĥжи
    -0.08
    æĹłäºĭ
    -0.06
     ''),
    -0.06
    ä¸ī两
    -0.06
     bravo
    -0.06
     <<-
    -0.06
    mans
    -0.06
    äºİ
    -0.06
    heids
    -0.06
    NotFoundError
    -0.06
    POSITIVE LOGITS
    าà¸Ħ
    0.08
    jit
    0.07
    รัà¸Ļ
    0.07
    rk
    0.07
    rais
    0.07
    erk
    0.07
    è¯
    0.07
    ast
    0.07
    poll
    0.07
    liegen
    0.07
    Activations Density 0.016%

    No Known Activations