© 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. 23550
    Prev
    Next
    INDEX
    Explanations

    "at" followed by Cards or Approach

    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
    计ç®Ĺåħ¬å¼ı
    -0.08
    åĪĩ
    -0.07
     formula
    -0.07
    æĮī
    -0.07
    butt
    -0.07
    égor
    -0.07
    chnet
    -0.07
    dech
    -0.06
    antine
    -0.06
    åħ¬å¼ı
    -0.06
    POSITIVE LOGITS
     Laurent
    0.07
    ä¹ĭå®Ŀ
    0.07
    èļ
    0.07
    çŀ°
    0.07
     backwards
    0.07
    浩çĢļ
    0.07
     Batista
    0.07
    BOSE
    0.06
    èħĶ
    0.06
    çĮķ
    0.06
    Activations Density 0.003%

    No Known Activations