© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 21902
    Prev
    Next
    INDEX
    Explanations

    lens optics

    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
    èĻİ
    -0.07
    builtin
    -0.07
    IMIT
    -0.07
    é«
    -0.07
    èĹķ
    -0.06
     кок
    -0.06
     manuals
    -0.06
    æĭ
    -0.06
    æį£
    -0.06
    ä¸ĭåİ»äºĨ
    -0.06
    POSITIVE LOGITS
     Lens
    0.11
    æķ£å°Ħ
    0.09
     lens
    0.09
     scattering
    0.09
    éĢıéķľ
    0.09
    éģ®æĮ¡
    0.09
    Lens
    0.09
    æīŃæĽ²
    0.08
    ãĥ¬ãĥ³ãĤº
    0.08
     lenses
    0.08
    Activations Density 0.010%

    No Known Activations