© 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. 19701
    Prev
    Next
    INDEX
    Explanations

    insight into understanding

    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
    ity
    -0.10
    ities
    -0.09
    zinho
    -0.09
    aseline
    -0.08
    ITY
    -0.08
    ality
    -0.08
    usco
    -0.08
    quet
    -0.08
    schaft
    -0.08
    ersistence
    -0.08
    POSITIVE LOGITS
    fully
    0.10
    pector
    0.09
    ħ
    0.09
    fulness
    0.09
     gained
    0.09
    ful
    0.08
    edly
    0.08
    ively
    0.08
     glean
    0.08
    端åĢª
    0.07
    Activations Density 0.018%

    No Known Activations