© 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. 1125
    Prev
    Next
    INDEX
    Explanations

    solid state, material, foods

    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
    èį¡æ¼¾
    -0.08
     pÅĤyn
    -0.08
    鬣
    -0.08
    æ¼¾
    -0.08
    æĹłéĺ»
    -0.08
    ä¸Ģæ»´
    -0.07
    æ±ĩåħ¥
    -0.07
    ersch
    -0.07
    åı£å¾Ħ
    -0.07
     flowing
    -0.07
    POSITIVE LOGITS
    åĽºä½ĵ
    0.12
    solid
    0.11
    -solid
    0.10
    åĿļ硬
    0.10
    Solid
    0.10
     solid
    0.10
    åĽº
    0.10
     Solid
    0.10
    åĽºæĢģ
    0.10
     ÑĤвеÑĢ
    0.10
    Activations Density 0.149%

    No Known Activations