© 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. 56883
    Prev
    Next
    INDEX
    Explanations

    information and details

    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
    kens
    -0.08
    å¤ļç§įæĸ¹å¼ı
    -0.07
    cke
    -0.07
    èĥ½åĬ¨
    -0.07
    oria
    -0.07
     chéo
    -0.07
    NonQuery
    -0.07
    以ä¸ĭåĩłç§į
    -0.07
    ãģĸãģ¾
    -0.07
    orias
    -0.07
    POSITIVE LOGITS
     details
    0.12
     particulars
    0.11
     parameters
    0.11
    parameters
    0.10
     characteristics
    0.10
    details
    0.10
    åıĤæķ°
    0.09
     Details
    0.09
    åĮħæĭ¬
    0.09
     specifications
    0.09
    Activations Density 0.525%

    No Known Activations