© 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. 39631
    Prev
    Next
    INDEX
    Explanations

    one, 1, hour, stone, int

    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
    uhe
    -0.08
    /master
    -0.07
     cát
    -0.07
    lte
    -0.07
    _hop
    -0.07
    itore
    -0.07
    è°İè¨Ģ
    -0.07
     Bakal
    -0.07
    íĤ
    -0.07
    claimer
    -0.07
    POSITIVE LOGITS
    amu
    0.07
    urt
    0.06
    鹿
    0.06
     bes
    0.06
    家éķ¿
    0.06
    å·²ä¹ħ
    0.06
    åı
    0.06
     strt
    0.06
     amt
    0.06
     e
    0.06
    Activations Density 0.002%

    No Known Activations