© 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. 33333
    Prev
    Next
    INDEX
    Explanations

    fluctuated, peak, since, record low/high

    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
    éĤij
    -0.08
    өг
    -0.08
    å±ĬæŶ
    -0.08
     demain
    -0.08
    åĪ°æŶåĢĻ
    -0.08
     amanhã
    -0.08
     tomorrow
    -0.08
    anz
    -0.08
    åģļ人
    -0.08
    quio
    -0.07
    POSITIVE LOGITS
     consistently
    0.08
     trend
    0.08
     recent
    0.08
     record
    0.08
     decade
    0.08
     epoch
    0.08
     steadily
    0.08
    å·ħå³°
    0.07
     plateau
    0.07
     peak
    0.07
    Activations Density 0.335%

    No Known Activations