© 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. 17434
    Prev
    Next
    INDEX
    Explanations

    melting point, temperature, curve, line

    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
    /method
    -0.08
     dilig
    -0.07
    onal
    -0.07
    erstellung
    -0.07
    人士
    -0.07
    ulary
    -0.07
    à¸ĵ
    -0.07
     longe
    -0.07
    suming
    -0.07
    stown
    -0.07
    POSITIVE LOGITS
    ency
    0.08
    /ref
    0.08
    èŀįåĮĸ
    0.07
    uzzi
    0.07
    ablish
    0.07
    çĨĶåĮĸ
    0.07
    /dis
    0.07
    ı
    0.07
    burg
    0.07
    /free
    0.07
    Activations Density 0.006%

    No Known Activations