© 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. 18450
    Prev
    Next
    INDEX
    Explanations

    mitochondrial gene fragments and regions

    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
     discharge
    -0.07
    缴è§ī
    -0.07
    æľīæĿĥ
    -0.07
     discharged
    -0.06
    quee
    -0.06
    è¯ķæİ¢
    -0.06
    æĹłçIJĨ
    -0.06
     Pilk
    -0.06
    olie
    -0.06
     rundown
    -0.06
    POSITIVE LOGITS
    éĩĩéĽĨ
    0.08
    ajak
    0.08
     fragments
    0.08
     fingerprint
    0.08
     gene
    0.08
    RYPT
    0.08
    éĢīåıĸ
    0.08
     fragment
    0.08
    pecies
    0.07
    arters
    0.07
    Activations Density 0.096%

    No Known Activations