© 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. 2715
    Prev
    Next
    INDEX
    Explanations

    organic compounds and demand

    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
     dispens
    -0.07
    upert
    -0.07
    unik
    -0.06
    plate
    -0.06
    è¡¥éĴĻ
    -0.06
    éĽ³
    -0.06
    outing
    -0.06
     disp
    -0.06
    imestone
    -0.06
    èħ°éħ¸
    -0.06
    POSITIVE LOGITS
    -rich
    0.09
    atables
    0.08
     richness
    0.08
    ụn
    0.07
    çī©è´¨
    0.07
    è¡ĢçĹĩ
    0.07
    èµ·æīĭ
    0.07
    浪
    0.07
    subclass
    0.07
     Carp
    0.07
    Activations Density 0.036%

    No Known Activations