© 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. 63780
    Prev
    Next
    INDEX
    Explanations

    encoding and decoding

    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
     fet
    -0.07
    渺
    -0.07
    iony
    -0.07
    à¹Ģà¸Ĺศ
    -0.07
    éĩĬæĶ¾
    -0.06
    funcs
    -0.06
     continuitÃł
    -0.06
    quam
    -0.06
     Boul
    -0.06
     kep
    -0.06
    POSITIVE LOGITS
     Encoding
    0.10
     encoding
    0.09
    èĭijå°ıåĮº
    0.08
    æĭīèĤļåŃIJ
    0.08
    è¡Įæķ°
    0.08
     encoder
    0.08
     decoder
    0.08
     Encode
    0.08
     encode
    0.08
     Spo
    0.08
    Activations Density 0.016%

    No Known Activations