© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 14637
    Prev
    Next
    INDEX
    Explanations

    vapor pressure and volatility

    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
    çºłæŃ£
    -0.08
     phì
    -0.07
    è´¨çĸij
    -0.06
     instantiation
    -0.06
    hattan
    -0.06
    æķĻè®Ń
    -0.06
    folgen
    -0.06
    棱è§Ĵ
    -0.06
    inheit
    -0.06
    ÃįN
    -0.06
    POSITIVE LOGITS
    å°ģ
    0.08
    pressure
    0.08
     atmosf
    0.08
    aglio
    0.08
     atmosfer
    0.08
    волÑĮ
    0.08
    ambar
    0.08
    å¯ĨéĹŃ
    0.08
    ilibrium
    0.08
     cling
    0.08
    Activations Density 0.004%

    No Known Activations