© 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. 34675
    Prev
    Next
    INDEX
    Explanations

    mathematical and scientific 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
    èĩªæĭħ
    -0.07
     (_
    -0.06
    ober
    -0.06
    annes
    -0.06
     назнаÑĩениÑı
    -0.06
    obod
    -0.06
    .tap
    -0.06
    ummer
    -0.06
     taped
    -0.05
    .Interop
    -0.05
    POSITIVE LOGITS
    ieux
    0.09
    ersp
    0.08
     bowiem
    0.08
    .physics
    0.08
     helst
    0.08
    çİĩåľ¨
    0.07
    iosa
    0.07
    è½»æĿ¾åľ°
    0.07
    æľĪ份å¼Ģå§ĭ
    0.07
    ÙĬÙħØ©
    0.07
    Activations Density 0.006%

    No Known Activations