© 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. 27960
    Prev
    Next
    INDEX
    Explanations

    evaluating reviews and approvals

    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
    %A
    -0.08
    RefCount
    -0.08
     lawy
    -0.08
    楷
    -0.08
    кÑĨиÑı
    -0.07
    %c
    -0.07
    èıģ
    -0.07
    SingleNode
    -0.07
     Breitbart
    -0.07
    æķ´ä½ĵçļĦ
    -0.07
    POSITIVE LOGITS
    è¯Ħ审
    0.08
    åĪ¤
    0.07
     evaluation
    0.07
    åĪ©äºļ
    0.07
    å®¡æŁ¥
    0.07
    è¯Ħä¼°
    0.07
     evalu
    0.07
    è¦ģæ±ĤåĴĮ
    0.07
     reviewers
    0.07
    åıĹçIJĨ
    0.07
    Activations Density 0.198%

    No Known Activations