© 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. 16032
    Prev
    Next
    INDEX
    Explanations

    corresponding to

    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
    erer
    -0.09
    éĩĮäºļ
    -0.08
    eren
    -0.08
    monic
    -0.08
    itek
    -0.08
    klang
    -0.08
    anity
    -0.08
    Bindable
    -0.08
    åı¯æĺ¯åľ¨
    -0.08
    imetr
    -0.08
    POSITIVE LOGITS
    Ø©
    0.15
    çļĦæĺ¯
    0.12
    ting
    0.10
    çĿĢ
    0.10
    çĿĢæĪij们çļĦ
    0.09
     nhau
    0.09
    a
    0.09
    ly
    0.08
    ness
    0.08
    wards
    0.07
    Activations Density 0.001%

    No Known Activations