© 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. 60410
    Prev
    Next
    INDEX
    Explanations

    exact or precise 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
    ieme
    -0.08
    çĭ¬ç«ĭ
    -0.07
    -hooks
    -0.07
    prim
    -0.07
     Bom
    -0.07
     Bub
    -0.07
     externally
    -0.07
    erso
    -0.07
    ï¼ł
    -0.07
    æ²¼
    -0.07
    POSITIVE LOGITS
     exact
    0.11
     Exact
    0.11
    _exact
    0.10
    精确
    0.10
    Exact
    0.10
    exact
    0.10
     instead
    0.09
     rather
    0.09
     precise
    0.08
    rather
    0.08
    Activations Density 0.096%

    No Known Activations