© 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. 15867
    Prev
    Next
    INDEX
    Explanations

    decimal numbers and sequences

    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
    å°½åħ¶
    -0.07
    esel
    -0.07
    isted
    -0.07
    ï¸İ
    -0.07
    Ä©
    -0.07
    iesen
    -0.06
    iega
    -0.06
    erve
    -0.06
    æ°ı
    -0.06
    à°Łà°¿
    -0.06
    POSITIVE LOGITS
    itm
    0.08
     Déb
    0.07
    æĹłæĢ¨æĹłæĤĶ
    0.07
    aal
    0.07
    ows
    0.07
    owska
    0.07
     Enf
    0.07
    owing
    0.07
    jenigen
    0.07
    大纲
    0.07
    Activations Density 0.012%

    No Known Activations