© 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. 31259
    Prev
    Next
    INDEX
    Explanations

    mitochondria

    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
     impun
    -0.09
    æĥ¯äºĨ
    -0.08
    æĸ°å¼Ģ
    -0.08
    itre
    -0.08
    quence
    -0.08
    ä»ĸ家
    -0.08
    Ñĥже
    -0.07
     antibio
    -0.07
    feit
    -0.07
     applicable
    -0.07
    POSITIVE LOGITS
     mitochond
    0.08
    寿åij½
    0.07
    à§Ģয়
    0.07
    rive
    0.07
    undle
    0.07
    iglio
    0.07
     mitochondrial
    0.07
    urrent
    0.07
    åĨħéĥ¨
    0.07
    ernals
    0.06
    Activations Density 0.028%

    No Known Activations