© 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. 20669
    Prev
    Next
    INDEX
    Explanations

    file extensions and code contexts

    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
    麻麻
    -0.07
    è¿ĻçĤ¹
    -0.06
    éĽĦé¹°
    -0.06
    èijµèĬ±
    -0.06
     previously
    -0.06
    кÑĢа
    -0.06
    éĩ
    -0.05
    _QUAL
    -0.05
    è¿Ļä¸ĢçĤ¹
    -0.05
     S
    -0.05
    POSITIVE LOGITS
    åĵªå®¶å¥½
    0.08
    gnose
    0.08
    车åĨµ
    0.08
    okal
    0.08
    管çIJĨçŃī
    0.07
    å¹´åħ¬åı¸
    0.07
     reivind
    0.07
    æĪijçıŃ
    0.07
    ä¸Ńå¿ĥçŃī
    0.07
    RouterModule
    0.07
    Activations Density 0.104%

    No Known Activations