© 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. 25620
    Prev
    Next
    INDEX
    Explanations

    numbers and time periods

    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
     slan
    -0.08
    FromClass
    -0.08
    ulam
    -0.07
    èİİæĭī
    -0.07
    enny
    -0.07
    ļĮ
    -0.07
    ilea
    -0.07
    .anim
    -0.07
    ÙĪÙĬÙĦ
    -0.07
    imiento
    -0.07
    POSITIVE LOGITS
     Vision
    0.06
    orne
    0.06
    ä½ĵéĩı
    0.06
    _runtime
    0.06
     vision
    0.06
    iph
    0.06
     plaint
    0.06
    bat
    0.06
     sank
    0.06
    akin
    0.06
    Activations Density 0.007%

    No Known Activations