© 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. 62537
    Prev
    Next
    INDEX
    Explanations

    element assembly

    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
    ä¸Ńæŀ¢
    -0.07
    ÙĪب
    -0.06
     prompt
    -0.06
     Ment
    -0.06
    çĪĨåıijçļĦ
    -0.06
    俱
    -0.06
    äºijå±Ĥ
    -0.06
     Rockefeller
    -0.06
     catal
    -0.06
     club
    -0.06
    POSITIVE LOGITS
    移
    0.08
     stiffness
    0.08
    åįķåħĥ
    0.08
    åįķåħĥçļĦ
    0.08
    ä½į移
    0.08
    ename
    0.08
    çŁ¥åħ¶
    0.08
    ç¼Ŀ
    0.07
    纳士
    0.07
    tlement
    0.07
    Activations Density 0.008%

    No Known Activations