© 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. 2518
    Prev
    Next
    INDEX
    Explanations

    electrical charge

    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
    upert
    -0.09
    å²Ń
    -0.08
    वार
    -0.08
    uvia
    -0.08
    ÑĢавни
    -0.07
    Neal
    -0.07
    ình
    -0.07
    bounds
    -0.07
    логов
    -0.07
    ebro
    -0.07
    POSITIVE LOGITS
    çĶµèį·
    0.09
     charges
    0.09
    æĢ»éĩı
    0.08
    éĿĻçĶµ
    0.08
     charge
    0.08
    éĩı
    0.08
     amount
    0.08
    æķ£
    0.08
    导ä½ĵ
    0.08
    åı²
    0.07
    Activations Density 0.001%

    No Known Activations