© 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. 39909
    Prev
    Next
    INDEX
    Explanations

    judge names and ECT codes

    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
    enje
    -0.07
    ìŬ
    -0.07
    è³ŀ
    -0.07
    &a
    -0.07
    оÑĤа
    -0.07
    üg
    -0.07
    &E
    -0.07
    ä¸Ģéĥİ
    -0.07
    icha
    -0.07
    athers
    -0.07
    POSITIVE LOGITS
    udos
    0.07
    Ŀ
    0.06
     probation
    0.06
    iffin
    0.06
    Sq
    0.06
    æŃ»æ´»
    0.06
    inian
    0.06
    鬣
    0.06
    aian
    0.06
    kke
    0.06
    Activations Density 1.430%

    No Known Activations