© 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. 21371
    Prev
    Next
    INDEX
    Explanations

    intermolecular and intramolecular interactions

    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
     optics
    -0.08
    sker
    -0.07
     clipped
    -0.07
    å°ıå°Ĩ
    -0.07
    å°ĸçļĦ
    -0.07
    åĨħ容æıIJä¾Ľæĸ¹
    -0.07
    çĤ¹åĩ»åı³ä¸Ĭè§Ĵ
    -0.07
    rollable
    -0.07
     ÑģкоÑĢ
    -0.07
     Ages
    -0.07
    POSITIVE LOGITS
     cohesion
    0.07
    沸çĤ¹
    0.07
    稳
    0.07
     inter
    0.07
    ç¼Ķ
    0.07
    建æľī
    0.07
    ç»Ĭ
    0.07
     benchmark
    0.07
    åĪĨåŃIJéĩı
    0.07
    è¾ĥéĩį
    0.07
    Activations Density 0.005%

    No Known Activations