© 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. 19148
    Prev
    Next
    INDEX
    Explanations

    keyword "returns" or "output"

    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
     Fare
    -0.08
    erner
    -0.08
    onet
    -0.08
    ãĤıãģĸ
    -0.08
    èĢĮå¤į
    -0.08
    å¤ļçĤ¹
    -0.08
    emens
    -0.07
    kus
    -0.07
    _UTF
    -0.07
    -pill
    -0.07
    POSITIVE LOGITS
    yll
    0.07
    Indented
    0.07
     result
    0.07
    /result
    0.07
    æĪĸ对
    0.07
    -decoration
    0.07
    .Result
    0.07
     berupa
    0.06
    .result
    0.06
    ç»ĵæŀľ
    0.06
    Activations Density 0.025%

    No Known Activations