© 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. 8785
    Prev
    Next
    INDEX
    Explanations

    explaining a situation

    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
     Cupertino
    -0.09
    enges
    -0.08
    eday
    -0.08
    æľī为
    -0.08
    èİ«æµĭ
    -0.08
    -leaning
    -0.07
    è¾»
    -0.07
    azes
    -0.07
    roud
    -0.07
    .createClass
    -0.07
    POSITIVE LOGITS
    çł¥
    0.08
    onn
    0.06
    并ç»Ħç»ĩ
    0.06
    èĻ½çĦ¶çİ°åľ¨
    0.06
    ilu
    0.06
     relevant
    0.06
    ادÙĩ
    0.06
    èĻ½è¯´
    0.06
    ono
    0.06
     situation
    0.06
    Activations Density 0.001%

    No Known Activations