© 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. 13866
    Prev
    Next
    INDEX
    Explanations

    parameter or number insertions

    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
     nutritional
    -0.06
    æľīåħ³çļĦ
    -0.06
     Re
    -0.06
    iol
    -0.06
    ез
    -0.06
    ÙħØŃ
    -0.05
    UCT
    -0.05
    åĩī
    -0.05
    æľīä¸Ģå®ļ
    -0.05
    æľīä¸Ģå®ļçļĦ
    -0.05
    POSITIVE LOGITS
    gings
    0.10
    öger
    0.09
    ä¸įè¡ĮäºĨ
    0.09
    åħ°è¾¾
    0.08
    gage
    0.08
    alism
    0.08
    ambang
    0.08
    quio
    0.08
    celona
    0.08
    ensing
    0.08
    Activations Density 0.001%

    No Known Activations