© 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. 31844
    Prev
    Next
    INDEX
    Explanations

    spatial recognition and distribution

    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
    anness
    -0.08
    zilla
    -0.07
     Äijặn
    -0.07
    ë°ĺ기
    -0.07
    ÙĨدÙĩ
    -0.07
    attet
    -0.07
    bara
    -0.07
    edly
    -0.07
    gers
    -0.07
    º
    -0.07
    POSITIVE LOGITS
    ly
    0.17
    mente
    0.13
    ï¸İ
    0.11
    Ø©
    0.10
    -temp
    0.10
    áŁĭ
    0.09
    lys
    0.08
    ually
    0.08
    å©·
    0.08
    ago
    0.08
    Activations Density 0.022%

    No Known Activations