© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 2918
    Prev
    Next
    INDEX
    Explanations

    carbon-silicon bond

    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
    .Zero
    -0.08
    WithValue
    -0.08
    大äºĭ
    -0.07
    era
    -0.07
    ç¾ŀ
    -0.07
    æľīåħ³è¦ģæ±Ĥ
    -0.07
    ä»Ģä¹Īéĥ½æ²¡
    -0.06
    è®Ĭ
    -0.06
    odings
    -0.06
    EqualityComparer
    -0.06
    POSITIVE LOGITS
    ạch
    0.08
     ($)
    0.07
    wort
    0.07
     Grat
    0.07
     bonded
    0.07
    orgh
    0.07
     dope
    0.07
    åĢŁåĬĽ
    0.07
    =%.
    0.07
    à¸ŀัà¸Ļà¸ĺ
    0.07
    Activations Density 0.016%

    No Known Activations