© 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. 9707
    Prev
    Next
    INDEX
    Explanations

    lymphocyte, lymph nodes, lymph vessels

    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
    ibir
    -0.08
     Civile
    -0.08
    Ŀ
    -0.08
    ampak
    -0.07
    agner
    -0.07
    anja
    -0.07
    以æľįåĬ¡
    -0.07
    ificio
    -0.07
    ocks
    -0.07
    gers
    -0.07
    POSITIVE LOGITS
    æĺ¯äººä½ĵ
    0.08
    atic
    0.08
    oid
    0.07
    åı£æīį
    0.07
    ocyte
    0.07
    ocytes
    0.07
    alo
    0.06
    èĤ¿å¤§
    0.06
    ester
    0.06
    ampu
    0.06
    Activations Density 0.035%

    No Known Activations