© 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. 30736
    Prev
    Next
    INDEX
    Explanations

    electrolyte and ionic liquid

    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
    çĦ¶å¤§
    -0.06
    çľģä¼ļ
    -0.06
    nst
    -0.06
     recur
    -0.06
     escal
    -0.06
     autos
    -0.06
    éĢĢè¿ĺ
    -0.06
     elev
    -0.06
     Liver
    -0.06
     Weiner
    -0.06
    POSITIVE LOGITS
    æµģåĭķ
    0.08
    urit
    0.08
    å½Į
    0.08
     வழ
    0.08
    bruch
    0.08
    å¼¥
    0.08
     angk
    0.08
    ëģĦ
    0.08
     immobil
    0.08
    æµģåĬ¨
    0.08
    Activations Density 0.022%

    No Known Activations