© 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. 60595
    Prev
    Next
    INDEX
    Explanations

    references and citations

    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
    ject
    -0.07
    æľīä¸Ģå®ļçļĦ
    -0.06
    appropri
    -0.06
    illar
    -0.06
    ung
    -0.06
    ä¹İ
    -0.06
    ев
    -0.06
    åĨħ侧
    -0.06
    ades
    -0.06
    -
    -0.06
    POSITIVE LOGITS
    tku
    0.08
    好çĶ¨çļĦ
    0.08
    ingga
    0.08
     >",
    0.07
    ลà¹Īาสุà¸Ķ
    0.07
     fras
    0.07
    ä¼ģä¸ļåIJĪä½ľ
    0.07
    olgen
    0.07
    âĸ·
    0.07
    _placeholder
    0.07
    Activations Density 0.005%

    No Known Activations