© 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. 51336
    Prev
    Next
    INDEX
    Explanations

    sheet algebra, internuclear separation, twisted bilayer, allogeneic transplantation, subduction style, gas phase

    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
     Beno
    -0.07
    ima
    -0.06
    ina
    -0.06
    é³Ħ
    -0.06
    kra
    -0.06
    çĶ¨æĪ·ä½¿çĶ¨
    -0.06
    ãĤªãĥªãĥ³
    -0.06
    ç»Ħ
    -0.06
    ebol
    -0.06
    (?)
    -0.06
    POSITIVE LOGITS
    çī¹æľī
    0.09
    ctx
    0.08
    -induced
    0.08
    unta
    0.07
    å°Ĩåĩºçİ°
    0.07
    íĻĺê²½
    0.07
    è¿ĺä¼ļåĩºçİ°
    0.07
    .features
    0.07
    -wide
    0.07
    -specific
    0.07
    Activations Density 0.054%

    No Known Activations