© 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. 9732
    Prev
    Next
    INDEX
    Explanations

    names, organizations, and years

    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
    ombok
    -0.06
    åľ¨å¿ħ
    -0.06
    æĹĹé¼ĵ
    -0.05
    æ¤ħ
    -0.05
    ping
    -0.05
    ï¸ı
    -0.05
    æł¹éĥ¨
    -0.05
     irreversible
    -0.05
     architectures
    -0.05
    说äºĨç®Ĺ
    -0.05
    POSITIVE LOGITS
     Desp
    0.08
     Seri
    0.08
    uvan
    0.07
    åħ°çī¹
    0.07
    Ø®ÙĨ
    0.07
    ints
    0.07
    мона
    0.07
    IBE
    0.07
    consts
    0.07
    zub
    0.07
    Activations Density 0.429%

    No Known Activations