© 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. 62076
    Prev
    Next
    INDEX
    Explanations

    magnetic field, electric field, trade winds, beam weapon

    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
    ebol
    -0.07
    åĢ©
    -0.07
     Ecology
    -0.07
    alaman
    -0.07
    ä¸ĬçļĦ
    -0.06
    çĶŁæĢģåѦ
    -0.06
    åĢĴæķ°
    -0.06
    èĩªæĪij
    -0.06
    åłµå¡ŀ
    -0.06
    å¿Ĺ
    -0.06
    POSITIVE LOGITS
     prostÅĻedÃŃ
    0.09
    à¹ģวà¸Ķลà¹īà¸Ńม
    0.08
    ä»ħæıIJä¾Ľ
    0.08
     hatás
    0.08
    ropole
    0.08
    feld
    0.07
    çĶµåľº
    0.07
     stationary
    0.07
    zers
    0.07
    æģĴå®ļ
    0.07
    Activations Density 0.012%

    No Known Activations