© 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. 16697
    Prev
    Next
    INDEX
    Explanations

    algorithm and approach

    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
    å¤ļ姿
    -0.07
    AMA
    -0.07
    .githubusercontent
    -0.06
    çĭĤ
    -0.06
     Truman
    -0.06
    èŀį为ä¸Ģä½ĵ
    -0.06
    urig
    -0.06
    éĹ®
    -0.06
    atra
    -0.06
    oliber
    -0.06
    POSITIVE LOGITS
     implementations
    0.10
     algorithms
    0.10
     solutions
    0.10
     solution
    0.10
    第äºĮç§į
    0.09
     scalable
    0.09
    解åĨ³éĹ®é¢ĺçļĦ
    0.09
     алгоÑĢиÑĤ
    0.09
    解åĨ³æĸ¹æ¡Ī
    0.09
    bish
    0.09
    Activations Density 0.087%

    No Known Activations