© 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. 49935
    Prev
    Next
    INDEX
    Explanations

    this + punctuation or following word

    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
    ä»ĩ
    -0.07
    åĴĮçĶ°
    -0.06
    大éĩı
    -0.06
    èį·
    -0.06
    ichel
    -0.06
    éĩįçĤ¹
    -0.06
    .future
    -0.06
    åij¼åIJ¸
    -0.06
    eref
    -0.06
    åĮºåŁŁåĨħ
    -0.06
    POSITIVE LOGITS
    abah
    0.09
    çĶ±é«ĺ
    0.08
    ä¸įéļ¾
    0.08
    çĪ±å²Ĺ
    0.07
    æĺ¯å¾Īæľī
    0.07
    esper
    0.07
    并ä¸įéļ¾
    0.07
    aperto
    0.07
    åİ»åIJ§
    0.07
    çľĭä¼¼
    0.07
    Activations Density 0.073%

    No Known Activations