© 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. 14550
    Prev
    Next
    INDEX
    Explanations

    opposite practice

    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
    লাম
    -0.09
    ANCEL
    -0.08
    çĤ¹æѤ
    -0.08
    endant
    -0.08
    agna
    -0.07
    bull
    -0.07
    _batches
    -0.07
    engen
    -0.07
    çĦ¶åIJİæł¹æį®
    -0.07
    gangs
    -0.07
    POSITIVE LOGITS
    ä¹Łå°±æĺ¯è¯´
    0.17
    åį³
    0.17
    åį³åľ¨
    0.16
    å°±æĺ¯è¯´
    0.16
    ãģ¤ãģ¾ãĤĬ
    0.14
     yani
    0.14
    åį³åĪ°
    0.14
     cioè
    0.14
     ÛĮعÙĨÛĮ
    0.14
     meaning
    0.13
    Activations Density 0.168%

    No Known Activations