© 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. 9045
    Prev
    Next
    INDEX
    Explanations

    charge and related concepts

    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
    erver
    -0.08
    ë¹Ī
    -0.08
    åŃ¦ä¹łåĪ°
    -0.07
    åĵªå¤©
    -0.07
    æľīå¥ĸ
    -0.07
    ieden
    -0.07
     Heights
    -0.07
    থা
    -0.07
    วà¸Ļ
    -0.07
    ptime
    -0.07
    POSITIVE LOGITS
     charge
    0.10
     charges
    0.10
    çĶµèį·
    0.09
     attracting
    0.09
    èį·
    0.09
    charge
    0.09
    -positive
    0.09
     заÑĢÑıд
    0.08
     attracts
    0.08
     attraction
    0.08
    Activations Density 0.028%

    No Known Activations