© 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. 41458
    Prev
    Next
    INDEX
    Explanations

    Stirling, efficiency, Grau, invention

    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
    亲æľĭ
    -0.08
    ä¸Ģæĭį
    -0.08
    ordat
    -0.08
    æı®
    -0.08
     getro
    -0.08
    icali
    -0.08
    æ¼¾
    -0.07
    ienti
    -0.07
    rown
    -0.07
    odu
    -0.07
    POSITIVE LOGITS
    abat
    0.07
    çĥŃæºIJ
    0.07
    çĥŃæ°´åĻ¨
    0.06
     Carn
    0.06
    ogos
    0.06
     maxim
    0.06
    anna
    0.06
    大å¸Ī
    0.06
    åľ¨é«ĺ温
    0.06
    Wheel
    0.06
    Activations Density 0.002%

    No Known Activations