© 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. 2617
    Prev
    Next
    INDEX
    Explanations

    Gaming, camera, MILF, film, NFL

    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
    chand
    -0.07
    ed
    -0.07
    ogan
    -0.07
    cc
    -0.07
    opa
    -0.06
    æĺ¯ä¼ļ
    -0.06
    chas
    -0.06
    并åģļ好
    -0.06
    jero
    -0.06
    opil
    -0.06
    POSITIVE LOGITS
     interfer
    0.07
    ricos
    0.07
    swer
    0.07
    å°ĶèĴĻ
    0.07
    schemas
    0.07
    ä¹ĸ
    0.07
    ä¸ĵæłıæĶ¶å½ķ该åĨħ容
    0.07
    缸çĪ±
    0.07
    æľ¬æĸĩ为
    0.06
    elper
    0.06
    Activations Density 0.285%

    No Known Activations