© 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. 48213
    Prev
    Next
    INDEX
    Explanations

    inference and implication

    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
    ibas
    -0.08
    egel
    -0.08
    .Stage
    -0.08
    åIJĪä½µ
    -0.07
    FUN
    -0.07
    ç³ĸå°¿
    -0.07
    ersed
    -0.07
    atetime
    -0.07
    mpl
    -0.07
    InstanceState
    -0.07
    POSITIVE LOGITS
     inferred
    0.10
     indirectly
    0.10
     implied
    0.09
    éĹ´æİ¥
    0.09
     ded
    0.08
     indirect
    0.08
     inference
    0.08
     indire
    0.08
    çļĦéĩįè¦ģä¾Ŀæį®
    0.08
     infer
    0.07
    Activations Density 0.152%

    No Known Activations