© 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. 60688
    Prev
    Next
    INDEX
    Explanations

    translation

    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
    ä¸įæ²»
    -0.08
     defenses
    -0.06
    éĵ®
    -0.06
    див
    -0.06
    å²Ĥ
    -0.06
    zijd
    -0.06
    çĽ¸æľĽ
    -0.06
    å©ļåIJİ
    -0.06
    è·Ĩ
    -0.06
    ä»»ä½ķä¸Ģæĸ¹
    -0.06
    POSITIVE LOGITS
    çĶŁäº§ç®¡çIJĨ
    0.08
    akis
    0.07
    Ñijн
    0.07
     Kese
    0.07
    elpers
    0.07
    illant
    0.07
    èĺĩ
    0.07
     ÙĪاÙĦØ¥ÙĨ
    0.07
    æĸĩåĮĸä¸Ń
    0.07
    åĭī
    0.07
    Activations Density 0.023%

    No Known Activations