© 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. 27128
    Prev
    Next
    INDEX
    Explanations

    the implied warranty

    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
    serter
    -0.09
    ابÛĮ
    -0.09
    shal
    -0.09
    رس
    -0.08
    éĺħè¯»æľ¬æĸĩåīį
    -0.08
    trys
    -0.08
    marshall
    -0.08
    itzer
    -0.08
    åĪ©çī©
    -0.08
    akash
    -0.08
    POSITIVE LOGITS
    er
    0.07
    ure
    0.07
    åı°
    0.07
    illustr
    0.06
    1
    0.06
    0
    0.06
    ation
    0.06
     Illustrated
    0.06
    0.06
     illustrated
    0.06
    Activations Density 0.093%

    No Known Activations