© 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. 24686
    Prev
    Next
    INDEX
    Explanations

    legal cases and academic texts

    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
    yser
    -0.07
    æĿĢæİī
    -0.06
    HASH
    -0.06
    æ°´çģ«
    -0.06
     next
    -0.06
     Counsel
    -0.06
    ORT
    -0.06
    nij
    -0.06
    gba
    -0.06
    ä¸ĭä¸Ģ页
    -0.06
    POSITIVE LOGITS
    ä½ľä¸º
    0.16
    ä½ľçĤº
    0.13
    åı¯ä»¥ä½ľä¸º
    0.13
    åģļ为
    0.13
    称为
    0.12
    èĢĮä½ľä¸º
    0.11
    åı¯ä½ľä¸º
    0.11
    被称为
    0.11
    稱çĤº
    0.10
     каÑĩеÑģÑĤве
    0.10
    Activations Density 0.922%

    No Known Activations