© 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. 8348
    Prev
    Next
    INDEX
    Explanations

    previous, old, or outdated information

    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
    angkal
    -0.09
    å§ĭèĩ³
    -0.08
    nip
    -0.08
    ä¸įåĪĨ
    -0.08
    rawn
    -0.08
    Susp
    -0.08
    ighed
    -0.07
     mong
    -0.07
    åĪ°æľī
    -0.07
    opensource
    -0.07
    POSITIVE LOGITS
    æŧçļĦ
    0.12
    æŧ
    0.12
     cũ
    0.11
     old
    0.10
    èĢģçļĦ
    0.10
     older
    0.10
    ä¸įä¼ļåĨį
    0.10
    åĽŀ顾
    0.10
    å·²ç»ıè¿ĩåİ»
    0.10
    å·²å®ĮæĪIJ
    0.10
    Activations Density 0.201%

    No Known Activations