© 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. 8962
    Prev
    Next
    INDEX
    Explanations

    Planck scale and weak scale

    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
    åĮ»ç§ij大åѦ
    -0.08
    блÑİ
    -0.08
    tori
    -0.08
    tura
    -0.08
    Season
    -0.08
    主æķĻ
    -0.08
    stät
    -0.07
     saison
    -0.07
    arris
    -0.07
    -season
    -0.07
    POSITIVE LOGITS
    å®ĩå®Ļ
    0.08
     cosm
    0.07
     scale
    0.07
     scaled
    0.07
     nan
    0.07
    scale
    0.07
    尺度
    0.07
    æ··æ²Į
    0.07
    客
    0.06
     Scale
    0.06
    Activations Density 0.003%

    No Known Activations