© 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. 3464
    Prev
    Next
    INDEX
    Explanations

    indices, unemployment, giant, aspect ratios

    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
    sworth
    -0.08
     Tre
    -0.08
    UINT
    -0.07
    озна
    -0.07
    okr
    -0.07
    _DIRS
    -0.07
    浩
    -0.07
    CLI
    -0.06
     Madd
    -0.06
    ä¸īçĶŁ
    -0.06
    POSITIVE LOGITS
    åį³
    0.13
    å®ļä¹ī为
    0.12
    æĮĩ
    0.12
    æĺ¯æĮĩ
    0.11
    åį³åĪ°
    0.11
    æĮĩçļĦæĺ¯
    0.11
     ÛĮعÙĨÛĮ
    0.10
    ì¦ī
    0.10
    åį³åľ¨
    0.10
    å°±æĺ¯æĮĩ
    0.10
    Activations Density 0.152%

    No Known Activations