© 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. 47279
    Prev
    Next
    INDEX
    Explanations

    sodium chloride and salts

    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
    念念
    -0.07
    个人è¡Į为
    -0.07
    éric
    -0.07
    inator
    -0.07
     ×Ķ×ij×Ļ
    -0.07
    社ä¼ļä¸Ĭ
    -0.07
    onti
    -0.07
    dw
    -0.06
    GUID
    -0.06
    _cuda
    -0.06
    POSITIVE LOGITS
    èĢĥçĤ¹
    0.07
     Mixed
    0.07
    ivit
    0.07
    avern
    0.07
    æ··
    0.07
    åºľ
    0.06
    åĮĸåIJĪ
    0.06
    oha
    0.06
    Mixed
    0.06
     salts
    0.06
    Activations Density 0.002%

    No Known Activations