© 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. 31056
    Prev
    Next
    INDEX
    Explanations

    said before

    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
     Stanton
    -0.07
    åijĹ
    -0.07
    lei
    -0.07
    acas
    -0.07
    åħľ
    -0.07
    ac
    -0.06
    çªŁ
    -0.06
    æĸ¯å¡Ķ
    -0.06
     Vortrag
    -0.06
    ળ
    -0.06
    POSITIVE LOGITS
    çī¹æĦı
    0.08
    prof
    0.07
    §
    0.07
    Tele
    0.07
    é£ŀå¾Ģ
    0.06
    zit
    0.06
    deel
    0.06
    imed
    0.06
    phasis
    0.06
    ungsver
    0.06
    Activations Density 0.003%

    No Known Activations