© 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. 58359
    Prev
    Next
    INDEX
    Explanations

    medical terms and conditions

    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
    åºĶå°½éĩı
    -0.08
    è±ģ
    -0.07
    Jvm
    -0.07
    符
    -0.07
    à¸Ńม
    -0.07
     intact
    -0.07
    ahlung
    -0.07
    ëħ¹
    -0.07
    achten
    -0.07
    åĪ¶
    -0.07
    POSITIVE LOGITS
     needed
    0.12
    ãģĮå¿ħè¦ģãģª
    0.11
     due
    0.11
    needed
    0.11
    å¿ħè¦ģæĢ§
    0.11
     Needed
    0.10
    æĺ¯åĽłä¸º
    0.10
    -needed
    0.10
    _needed
    0.10
    éĥ½æĺ¯åĽłä¸º
    0.10
    Activations Density 0.408%

    No Known Activations