© 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. 30475
    Prev
    Next
    INDEX
    Explanations

    generally associated with

    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
    chs
    -0.10
    河山
    -0.09
    ispers
    -0.08
    uteurs
    -0.08
    å§Ĩæĸ¯
    -0.08
    emos
    -0.08
    emsp
    -0.08
    ecca
    -0.08
    èī²åĪĹ
    -0.08
    _information
    -0.08
    POSITIVE LOGITS
    O
    0.07
    è¿Ľä¸ĢæŃ¥
    0.07
     further
    0.06
    è¿Ľä¸ĢæŃ¥å¼ºåĮĸ
    0.06
    è¢
    0.06
    inning
    0.06
    奥
    0.06
     Prime
    0.05
    åºı
    0.05
     O
    0.05
    Activations Density 0.633%

    No Known Activations