© 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. 18094
    Prev
    Next
    INDEX
    Explanations

    forming somite

    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
    ãĤ³ãĥ¼ãĥ«
    -0.07
    太ä¸Ĭ
    -0.07
    被æµıè§Ī
    -0.07
    éĥİ
    -0.07
    oin
    -0.06
    akit
    -0.06
    顺åı£
    -0.06
    omentum
    -0.06
     ê³Ħ
    -0.06
    æĥ¯
    -0.06
    POSITIVE LOGITS
    æĬĵèIJ½å®ŀ
    0.08
     swapped
    0.07
    zada
    0.07
    å®ļçĤ¹
    0.07
    ipl
    0.07
    DataStream
    0.07
    ¯
    0.07
    å½Ĵ
    0.07
    å®īæİĴ好
    0.07
    spo
    0.07
    Activations Density 0.001%

    No Known Activations