© 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. 55841
    Prev
    Next
    INDEX
    Explanations

    knowledge and education

    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
    wein
    -0.06
    utter
    -0.06
     unpredictable
    -0.06
    æĬĢæľ¯åĪĽæĸ°
    -0.06
    åĪĽæĸ°æĢ§
    -0.06
    azar
    -0.06
    osals
    -0.06
    zar
    -0.06
    agram
    -0.06
    ãĤĴè¦ĭãĤĭãģ¨
    -0.06
    POSITIVE LOGITS
     knowledge
    0.14
    knowledge
    0.13
     Kenntnis
    0.13
    çŁ¥æĻĵ
    0.13
    çŁ¥éģĵ
    0.12
     Knowledge
    0.12
    çŁ¥ãĤĭ
    0.12
     know
    0.12
    äºĨ解
    0.12
    çŁ¥éģĵçļĦ
    0.12
    Activations Density 0.212%

    No Known Activations