© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 64278
    Prev
    Next
    INDEX
    Explanations

    viewfinders are brighter

    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
    åĩ¤åĩ°ç½ij
    -0.07
    .house
    -0.07
    å°½
    -0.07
    缮æłĩæĺ¯
    -0.06
    zd
    -0.06
    éģĵ
    -0.06
    assy
    -0.06
    çĽ¡
    -0.06
    éĺģ
    -0.06
    	elem
    -0.06
    POSITIVE LOGITS
    å¤ĩ注
    0.10
    åIJį称
    0.08
     rowspan
    0.08
    ä¸Ģè§Ī表
    0.07
    人家
    0.07
     (%)
    0.07
    ר×Ķ
    0.07
     Keterangan
    0.07
    ativa
    0.07
    abela
    0.07
    Activations Density 0.211%

    No Known Activations