© 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. 32724
    Prev
    Next
    INDEX
    Explanations

    asked me to

    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
    Enough
    -0.07
    pes
    -0.07
    æijĦ
    -0.07
    abler
    -0.06
    _UTF
    -0.06
    为ä¿Ŀè¯ģ
    -0.06
     emp
    -0.06
    æĥ³åľ¨
    -0.06
    å·²åIJij
    -0.06
    ecter
    -0.06
    POSITIVE LOGITS
    ç®Ĺä»Ģä¹Ī
    0.08
    .Tensor
    0.07
    并èĮĤ
    0.07
    ruise
    0.07
    çļĦå¿ĥèĦı
    0.07
    çois
    0.07
    åĮĸ身
    0.07
    ovil
    0.07
    æľĪ以æĿ¥
    0.07
    rane
    0.07
    Activations Density 0.004%

    No Known Activations