© 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. 24049
    Prev
    Next
    INDEX
    Explanations

    salts and acids

    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
    ility
    -0.08
    olem
    -0.08
    ót
    -0.08
    ilité
    -0.07
    ijo
    -0.07
    elij
    -0.07
    æĹ¥æ¶Īæģ¯
    -0.07
    issima
    -0.07
    讳
    -0.07
    æĹłä¸Ģ
    -0.07
    POSITIVE LOGITS
    建æĸ°
    0.07
    ação
    0.07
     splitting
    0.07
     Coff
    0.07
    åIJĪ
    0.07
    okes
    0.06
    manos
    0.06
     spans
    0.06
    åĪĨè£Ĥ
    0.06
    åĽ½å®¶éĩįçĤ¹
    0.06
    Activations Density 0.012%

    No Known Activations