© 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. 20485
    Prev
    Next
    INDEX
    Explanations

    variables with operators

    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
    å±±ä¸ĭ
    -0.07
    access
    -0.07
    ç«¥
    -0.07
    imun
    -0.07
    avar
    -0.07
    baum
    -0.07
    acon
    -0.07
    ãģĭãĤı
    -0.06
    onga
    -0.06
    èĢĮå¤į
    -0.06
    POSITIVE LOGITS
    æİ
    0.07
    èĤ©
    0.07
    ัà¸Ĺ
    0.07
    รà¸Ńย
    0.07
    enny
    0.07
    aturen
    0.07
     spoken
    0.06
    ix
    0.06
    ajak
    0.06
    åŃ
    0.06
    Activations Density 0.010%

    No Known Activations