© 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. 51732
    Prev
    Next
    INDEX
    Explanations

    salinity and salt content

    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
    åħīçĽĺ
    -0.08
    è´¢åĬĽ
    -0.07
    æĭ¨æ¬¾
    -0.07
    ìĹ½
    -0.07
    麻çĸ¹
    -0.06
    chers
    -0.06
    ervi
    -0.06
     dilig
    -0.06
     Cunha
    -0.06
     hood
    -0.06
    POSITIVE LOGITS
    çĽIJ
    0.12
     salt
    0.12
    åĴ¸
    0.10
     salty
    0.10
    é¹½
    0.10
     salts
    0.10
    æµ·æ°´
    0.09
     Salz
    0.09
    salt
    0.09
    Salt
    0.09
    Activations Density 0.025%

    No Known Activations