© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 14197
    Prev
    Next
    INDEX
    Explanations

    character selections with probabilities

    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
    baugh
    -0.07
    elo
    -0.06
    åĬłä¸Ĭ
    -0.06
    itale
    -0.06
    etre
    -0.06
    ä»ĭçŁ³
    -0.06
     hale
    -0.06
     Navarro
    -0.06
    è¿ŀ带责任
    -0.05
    æī¿
    -0.05
    POSITIVE LOGITS
    è½
    0.08
    azz
    0.08
    æĬŀ
    0.07
    æīĭå½ĵ
    0.07
    казÑĭ
    0.07
    Ĥ¬
    0.07
    íıŃ
    0.07
     niem
    0.07
    ruppe
    0.07
    _fx
    0.07
    Activations Density 0.012%

    No Known Activations