© 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. 50897
    Prev
    Next
    INDEX
    Explanations

    impact and energy dissipation

    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
    scri
    -0.07
    çĤľ
    -0.07
    å®ļæľŁ
    -0.07
    渴
    -0.07
     priesthood
    -0.07
    æĹºçĽĽ
    -0.07
    ÑĤÑĢе
    -0.07
     Skinny
    -0.07
     skinny
    -0.07
    ijk
    -0.07
    POSITIVE LOGITS
    åĨ²åĩ»åĬĽ
    0.12
     амоÑĢÑĤи
    0.10
    åĨ²åĩ»
    0.09
     padded
    0.09
    ernaut
    0.08
     biome
    0.08
    æļ´åĬĽ
    0.08
     compress
    0.08
    ç¼ĵåĨ²
    0.08
     dissip
    0.08
    Activations Density 0.056%

    No Known Activations