© 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. 40056
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and numbers

    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
    å¸ĥä¸ģ
    -0.08
    족
    -0.08
    å¡ĺéķĩ
    -0.08
    icamente
    -0.07
    åIJİéĢĢ
    -0.07
    æľ¬ç¯ĩ
    -0.07
    çī¹æѤ
    -0.07
    oty
    -0.07
    达峰
    -0.07
    ÏģοÏħÏĤ
    -0.07
    POSITIVE LOGITS
     “
    0.06
    åĪ©æ°ij
    0.06
    toUpperCase
    0.06
    æł¹æľ¬
    0.06
    umm
    0.06
    _FT
    0.06
    avana
    0.06
    wf
    0.06
    åĪºæ¿Ģ
    0.06
    æĭĤ
    0.06
    Activations Density 0.111%

    No Known Activations