© 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. 63086
    Prev
    Next
    INDEX
    Explanations

    returning or leaving

    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
     zwar
    -0.10
    OTES
    -0.08
    ÑĢÑĥÑĤ
    -0.08
    mula
    -0.07
    INED
    -0.07
    ода
    -0.07
    .directory
    -0.07
    |string
    -0.07
     )"
    -0.07
    statt
    -0.07
    POSITIVE LOGITS
     thereafter
    0.09
    åıĪ被
    0.08
    åĨįåĪ°
    0.07
    rase
    0.07
     again
    0.07
    ä¸įçĦ¶
    0.07
    çĶļ
    0.07
    avel
    0.07
     afterward
    0.06
    åĨįçĶ±
    0.06
    Activations Density 0.147%

    No Known Activations