© 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. 25795
    Prev
    Next
    INDEX
    Explanations

    plasticizers, mechanical, state, relaxations

    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
    ç§įèĭĹ
    -0.07
    çĩĥçħ¤
    -0.07
    è¾ĵåįµ
    -0.07
    è¡Ģèī²
    -0.07
    Ä°Z
    -0.06
    èį£èªīæĦŁ
    -0.06
    Õ²
    -0.06
    çģ¼
    -0.06
     exact
    -0.06
     Leaving
    -0.06
    POSITIVE LOGITS
    常温
    0.08
     transitions
    0.08
    室温
    0.07
    çĿģ
    0.07
     DMA
    0.07
    onton
    0.07
    åĬ©åīĤ
    0.07
     onset
    0.07
    below
    0.07
     craz
    0.07
    Activations Density 0.015%

    No Known Activations