© 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. 52070
    Prev
    Next
    INDEX
    Explanations

    domain-specific 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
    Negative Logits
    ttö
    -0.08
    aved
    -0.08
    ÏĦοÏħÏĤ
    -0.07
    Offsets
    -0.07
    /Framework
    -0.07
    adle
    -0.07
    Clr
    -0.07
    æŀī
    -0.07
    ÙĤÙĦØ©
    -0.07
    áĢ¹
    -0.07
    POSITIVE LOGITS
    -
    0.07
    +
    0.07
    -centric
    0.06
    æ¯Ķä½ľ
    0.06
    raw
    0.06
    ims
    0.06
    以å¤ĸçļĦ
    0.06
    èĥĨ
    0.06
    -specific
    0.06
    åı²ä¸ĬçļĦ
    0.06
    Activations Density 1.037%

    No Known Activations