© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 17155
    Prev
    Next
    INDEX
    Explanations

    calculating examples

    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
    çĻ»
    -0.08
     lehetÅij
    -0.07
    ä½łæĺ¯è°ģ
    -0.07
     entirety
    -0.06
    é¹°
    -0.06
     necess
    -0.06
    åĬłåĪĨ
    -0.06
    å°ļ
    -0.06
    defin
    -0.06
     DEFINE
    -0.06
    POSITIVE LOGITS
    ableView
    0.09
    æłĩåĩĨ为
    0.08
    lå
    0.08
     calculation
    0.08
    alculate
    0.08
    åĨįæľī
    0.08
     hypoth
    0.08
    Calculate
    0.08
     calculations
    0.08
    å¹´å¹³åĿĩ
    0.08
    Activations Density 0.026%

    No Known Activations