© 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. 30428
    Prev
    Next
    INDEX
    Explanations

    ionic strength and concentration

    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
    mlin
    -0.08
    Ñħодом
    -0.08
    èĭĵ
    -0.07
    èľĵ
    -0.07
    åIJ¸è¡Ģ
    -0.07
     Ultim
    -0.07
    .wr
    -0.07
    åıªæľīä¸Ģ次
    -0.07
    绿èī²å»ºçŃij
    -0.07
    çĩĥ
    -0.07
    POSITIVE LOGITS
    -spacing
    0.08
    çݯå¢ĥ
    0.08
    oglob
    0.08
    æĭ¥æĮ¤
    0.07
    ç¼ĵåĨ²
    0.07
     kos
    0.07
    æ·»åĬł
    0.07
    enner
    0.07
    æĶĺ
    0.07
    å±ıèĶ½
    0.07
    Activations Density 0.057%

    No Known Activations