© 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. 38644
    Prev
    Next
    INDEX
    Explanations

    probability questions

    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
    以
    -0.07
    以å°ı
    -0.06
    utra
    -0.06
    客
    -0.06
    Spaces
    -0.06
     Ha
    -0.06
    æīĢ
    -0.06
    warts
    -0.06
    quests
    -0.06
    åıĸæĿIJ
    -0.06
    POSITIVE LOGITS
    clare
    0.08
    eph
    0.08
    laus
    0.08
    aiser
    0.08
    åģľéĿł
    0.07
    asca
    0.07
    ccio
    0.07
    éc
    0.07
    eci
    0.07
    深水
    0.07
    Activations Density 0.043%

    No Known Activations