© 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. 47078
    Prev
    Next
    INDEX
    Explanations

    price and value

    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
    ansa
    -0.07
    è«
    -0.07
    ún
    -0.07
     ETA
    -0.07
     stanza
    -0.06
    atest
    -0.06
    çºĸ
    -0.06
    åĬ³éĢ¸
    -0.06
    æµģéĩı
    -0.06
     subsystem
    -0.06
    POSITIVE LOGITS
     ÏĥÏħνα
    0.09
    iffe
    0.08
    ingham
    0.08
    ×ķצ
    0.08
    reshold
    0.08
    LAR
    0.08
    izzer
    0.08
    -date
    0.08
    procs
    0.07
    海天
    0.07
    Activations Density 0.002%

    No Known Activations