© 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. 40962
    Prev
    Next
    INDEX
    Explanations

    mitochondrial DNA mutations and heterogeneity

    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
    riend
    -0.08
     dummy
    -0.07
    åıĭè°Ĭ
    -0.07
    èĬ·
    -0.07
     Dummy
    -0.07
    rut
    -0.07
    åıĭ
    -0.07
    dummy
    -0.07
    ä¼´ä½ł
    -0.06
    ummies
    -0.06
    POSITIVE LOGITS
     viability
    0.09
    ç»Ĩèĥŀ
    0.09
     progen
    0.09
     clones
    0.09
    åħĭéļĨ
    0.09
     mosaic
    0.08
     cells
    0.08
    UID
    0.08
    åŃĺæ´»
    0.08
     sampling
    0.08
    Activations Density 0.089%

    No Known Activations