© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 20135
    Prev
    Next
    INDEX
    Explanations

    technical field

    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¿Ĺæĺİ
    -0.08
    åĪ©æĸ¯
    -0.08
     fronte
    -0.08
    udios
    -0.08
    -tm
    -0.08
    Paused
    -0.08
    даÑħ
    -0.08
    çĺ¢
    -0.08
    å±ķå¼Ģåħ¨æĸĩ
    -0.08
    _palette
    -0.08
    POSITIVE LOGITS
    ä¼
    0.06
     lays
    0.06
    ween
    0.06
    æĶ
    0.06
    ares
    0.06
    ...
    0.06
    /background
    0.06
    æ¦Ĥè¿°
    0.06
    åĴĮåĨħ容
    0.06
    å¶
    0.06
    Activations Density 0.457%

    No Known Activations