© 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. 8501
    Prev
    Next
    INDEX
    Explanations

    numbers and abbreviations

    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
    etch
    -0.07
    zeug
    -0.07
    çı
    -0.07
    shift
    -0.07
    anch
    -0.07
    empo
    -0.07
    antage
    -0.07
    amar
    -0.06
    åĶ¾
    -0.06
    stead
    -0.06
    POSITIVE LOGITS
    eid
    0.07
    zza
    0.06
    åĽ²
    0.06
    ogi
    0.06
    нив
    0.06
    æľªç»ı
    0.06
    æķ¦
    0.06
    elin
    0.06
    审
    0.06
    QualifiedName
    0.06
    Activations Density 0.243%

    No Known Activations