© 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. 20865
    Prev
    Next
    INDEX
    Explanations

    voltage drop / pressure gradient

    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
    osomes
    -0.08
    ceaux
    -0.08
    InBackground
    -0.08
    æ¹ĸéĩĮ
    -0.08
    .openg
    -0.08
    ä¸įæĹ©
    -0.08
    biz
    -0.07
    ulous
    -0.07
     ancestry
    -0.07
    ä¸įç»ı
    -0.07
    POSITIVE LOGITS
    agg
    0.07
    çĶµåİĭ
    0.07
    anza
    0.07
    è¾ĵåĩºçĶµåİĭ
    0.07
    éĺ»
    0.07
    å¨ģé£İ
    0.06
    hou
    0.06
    resso
    0.06
     volt
    0.06
     buz
    0.06
    Activations Density 0.005%

    No Known Activations