© 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. 12540
    Prev
    Next
    INDEX
    Explanations

    code types: boolean, Object, Array, Number

    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
    ä½ĻæĿŃ
    -0.07
    ãģ¿ãģ®
    -0.07
     Schmid
    -0.06
    owitz
    -0.06
    ï½ŀãĢį
    -0.06
    YZ
    -0.06
     Belle
    -0.06
    olith
    -0.06
    äºĨåij¢
    -0.06
     Berl
    -0.06
    POSITIVE LOGITS
     conto
    0.08
    æĥķ
    0.07
    uncio
    0.07
    imbau
    0.07
    auch
    0.07
    anan
    0.07
    åijĹ
    0.07
    awl
    0.06
    elo
    0.06
    ése
    0.06
    Activations Density 0.001%

    No Known Activations