© 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. 9131
    Prev
    Next
    INDEX
    Explanations

    css property names and values

    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
    ope
    -0.07
    æģIJ
    -0.06
     strat
    -0.06
    èĥ
    -0.06
    åĤ
    -0.06
    æļĤæĹł
    -0.06
    åħ¨èº«
    -0.06
    O
    -0.06
    åĨį说
    -0.06
    holm
    -0.05
    POSITIVE LOGITS
    æłĩåĩĨè¦ģæ±Ĥ
    0.08
    ambul
    0.08
    entif
    0.08
    åħ¶ä¸ŃçļĦ
    0.08
    rific
    0.08
    aths
    0.08
    ErrorMsg
    0.08
     رب
    0.08
    idem
    0.08
    reden
    0.07
    Activations Density 0.016%

    No Known Activations