© 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. 38808
    Prev
    Next
    INDEX
    Explanations

    actions and their outcomes

    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
     itself
    -0.08
     its
    -0.08
     Its
    -0.07
    Its
    -0.07
    its
    -0.06
    éb
    -0.06
    åľ¨å®ĥ
    -0.06
    æĪijèĩªå·±çļĦ
    -0.06
    ÙĩÙħا
    -0.06
    à¸Ķัà¸ĩà¸ģลà¹Īาว
    -0.06
    POSITIVE LOGITS
     themselves
    0.17
     Ø£ÙĨÙģسÙĩÙħ
    0.14
     thems
    0.12
    ')))
    0.11
    ä½Ĩæĺ¯ä»ĸ们
    0.11
    ä»ĸ们çĶ¨
    0.10
    ä»ĸ们éľĢè¦ģ
    0.10
    æīĢ以ä»ĸ们
    0.10
    ä»ĸ们æīĢ
    0.10
    ä»ĸ们å°Ĩ
    0.10
    Activations Density 0.229%

    No Known Activations