© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 14778
    Prev
    Next
    INDEX
    Explanations

    Carbon dating

    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
    imizer
    -0.08
    èĵĿå®ĿçŁ³
    -0.08
    è¸
    -0.07
    åħ¬èĭ±
    -0.07
    vertret
    -0.07
    å¾ħå®ļ
    -0.07
    utory
    -0.07
     kumpulan
    -0.07
     congest
    -0.07
    issy
    -0.07
    POSITIVE LOGITS
    碳
    0.09
     carbon
    0.09
     charcoal
    0.09
    çĤŃ
    0.08
     Carbon
    0.08
    Carbon
    0.08
     decay
    0.08
    carbon
    0.08
     carbono
    0.08
     detection
    0.07
    Activations Density 0.006%

    No Known Activations