© 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. 41280
    Prev
    Next
    INDEX
    Explanations

    names and references

    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
    èįIJ
    -0.07
    iors
    -0.06
    åºŁè¯Ŀ
    -0.06
    studio
    -0.06
    ä»»éĩį
    -0.06
    注
    -0.06
    çĽĸä¸Ĭ
    -0.06
    CHAT
    -0.06
    å®ĮæĪIJåIJİ
    -0.06
    éĩijåŃIJ
    -0.06
    POSITIVE LOGITS
    åĩºçİ°åľ¨
    0.12
    使çĶ¨æŶ
    0.11
     appearing
    0.11
    åĩºçİ°åľ¨äºĨ
    0.11
    åĩºçı¾åľ¨
    0.11
    åĩºçİ°çļĦ
    0.10
    å¼ķçĶ¨çļĦ
    0.10
     throughout
    0.10
     Appe
    0.10
    appe
    0.10
    Activations Density 0.267%

    No Known Activations