© 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. 4391
    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
    udit
    -0.08
    çī¹æĸ°
    -0.08
    ÑĢÑı
    -0.08
    singleton
    -0.08
    oday
    -0.08
    次éĺħ读
    -0.08
    åĪĢçīĩ
    -0.07
    -fetch
    -0.07
    rib
    -0.07
    uggy
    -0.07
    POSITIVE LOGITS
    æĺ¯éĿŀ
    0.07
     steps
    0.06
    arith
    0.06
    å¾Īä¹ħ
    0.06
     Elimin
    0.06
    ä¸įæīĵ
    0.06
    astro
    0.06
     repeatedly
    0.06
     safer
    0.06
    å¼Ģ
    0.06
    Activations Density 0.003%

    No Known Activations