© 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. 63722
    Prev
    Next
    INDEX
    Explanations

    liquid crystal and related compositions

    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
    çī¹åĭĴ
    -0.09
    plit
    -0.08
    htag
    -0.08
    å¾Ĺèµ·
    -0.08
    oriously
    -0.08
    rawdÄĻ
    -0.08
    pty
    -0.08
    eon
    -0.08
    eo
    -0.08
    åĿĢ
    -0.08
    POSITIVE LOGITS
    zny
    0.09
    à¸Ļà¹īำ
    0.08
    inary
    0.08
    /o
    0.08
    ually
    0.08
    erna
    0.08
    dragon
    0.07
    ificador
    0.07
    ensed
    0.07
    ighthouse
    0.07
    Activations Density 0.021%

    No Known Activations