© 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. 4351
    Prev
    Next
    INDEX
    Explanations

    class names and terms

    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
    ×Ļ×ķת
    -0.07
    rän
    -0.06
    est
    -0.06
     Heb
    -0.06
    favor
    -0.06
     Pier
    -0.06
    ndo
    -0.06
    dee
    -0.06
    pars
    -0.06
    =p
    -0.06
    POSITIVE LOGITS
    ocale
    0.08
    onter
    0.08
    ä¸ĵæłıæĶ¶å½ķ该åĨħ容
    0.07
    å¸ĥ伦
    0.07
    éĽĨåĽ¢æĹĹä¸ĭ
    0.07
    æı©
    0.07
    第äºĮåįģ
    0.07
    æĪijæľīä¸Ģ个
    0.07
    oteles
    0.06
    úde
    0.06
    Activations Density 0.395%

    No Known Activations