© 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. 62313
    Prev
    Next
    INDEX
    Explanations

    knowledge and understanding

    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
    ita
    -0.07
    arty
    -0.07
    å®ľ
    -0.07
    ยาย
    -0.07
    validators
    -0.07
     Er
    -0.06
    å¦Ĥæŀľåı¯ä»¥
    -0.06
    çĶŁè®¡
    -0.06
    (?:
    -0.06
    æĦıè§ģ书
    -0.06
    POSITIVE LOGITS
    æİĮæı¡
    0.12
    çIJĨ解
    0.11
     understanding
    0.11
     understands
    0.10
     understand
    0.10
    æīįèĥ½æĽ´å¥½åľ°
    0.10
    æĬĬæı¡
    0.10
     comprendere
    0.09
    äºĨ解
    0.09
     memahami
    0.09
    Activations Density 0.119%

    No Known Activations