© 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. 8648
    Prev
    Next
    INDEX
    Explanations

    numbers following parentheses

    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
    å¤ľæ·±
    -0.07
    ãĤħãģĨ
    -0.07
    绪
    -0.07
    åħ¬çĽĬäºĭä¸ļ
    -0.07
    gether
    -0.07
    ool
    -0.06
    çĥ«
    -0.06
    antas
    -0.06
    ly
    -0.06
    建ä»ĵ
    -0.06
    POSITIVE LOGITS
    éĢģåİ»
    0.07
    bole
    0.07
    é½
    0.07
    ikal
    0.07
    égor
    0.07
     therein
    0.07
    å°±è¿Ļä¹Ī
    0.07
    æ³ķçŃī
    0.06
    -conf
    0.06
    许åı¯åĨħ容
    0.06
    Activations Density 0.025%

    No Known Activations