© 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. 43499
    Prev
    Next
    INDEX
    Explanations

    gramming, maps, derivatives, long-ranged

    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
    大åIJĮ
    -0.08
    aiss
    -0.08
    mpl
    -0.08
    éŀł
    -0.08
    urga
    -0.08
    缮å®ī
    -0.07
    ä¸į论
    -0.07
    atte
    -0.07
    å±ĪæĮĩ
    -0.07
    adera
    -0.07
    POSITIVE LOGITS
    æĪĸå¤ļ
    0.08
     accommodating
    0.08
    è¿Ļæĺ¯çĶ±äºİ
    0.08
    åĴĮå¤ļ
    0.08
     unconventional
    0.07
     arise
    0.07
    éļIJéļIJ
    0.07
    æĪĸéĿŀ
    0.07
     допÑĥÑģка
    0.07
    ãģĸãĤĭ
    0.07
    Activations Density 0.090%

    No Known Activations