© 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. 14382
    Prev
    Next
    INDEX
    Explanations

    invariant statistics, SEL, variant, vent

    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
     matched
    -0.07
    atched
    -0.07
     Asal
    -0.07
     Suatu
    -0.07
    (match
    -0.07
    elus
    -0.07
    并æī¿æĭħ
    -0.06
    isis
    -0.06
    äºĶ常
    -0.06
    quil
    -0.06
    POSITIVE LOGITS
    -Sah
    0.07
    Invariant
    0.07
     invariant
    0.07
     combinations
    0.07
    _PROXY
    0.07
     UIL
    0.07
    å±ĪæĮĩ
    0.07
    idane
    0.07
    PropertyDescriptor
    0.07
    ç»ĦåIJĪ
    0.07
    Activations Density 0.006%

    No Known Activations