© 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. 27322
    Prev
    Next
    INDEX
    Explanations

    biodegradable

    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
    åħ¨åı°
    -0.08
    çī¹éĴ¢
    -0.08
    ä¸įèĪį
    -0.08
    ictured
    -0.07
    argon
    -0.07
    亨
    -0.07
    ãĥĭãĥ¼
    -0.07
     discipl
    -0.07
    ¤
    -0.07
    quete
    -0.07
    POSITIVE LOGITS
    able
    0.09
    gradable
    0.09
    ABLE
    0.08
    /end
    0.08
    orable
    0.08
    /rec
    0.07
     organic
    0.07
    ables
    0.07
    izable
    0.07
    æľŁéĻIJåĨħ
    0.07
    Activations Density 0.045%

    No Known Activations