© 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. 34307
    Prev
    Next
    INDEX
    Explanations

    inheritance, transmission, reproduction

    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
    çªĥ
    -0.08
    ipas
    -0.08
    allon
    -0.08
    inee
    -0.08
    icode
    -0.07
    士ãģ®
    -0.07
    incon
    -0.07
    alysis
    -0.07
    oney
    -0.07
     sát
    -0.07
    POSITIVE LOGITS
     transmission
    0.11
    ä¼łéĢĴ
    0.10
    ä¼łæī¿
    0.09
     reproduction
    0.09
     Transmission
    0.09
     cycles
    0.09
    Transmission
    0.09
    åŃIJåŃĻ
    0.09
     cycle
    0.09
    ä¼łæĴŃ
    0.08
    Activations Density 0.058%

    No Known Activations