© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 4660
    Prev
    Next
    INDEX
    Explanations

    unclear

    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
    Negative Logits
    åĪĢ
    -0.07
    _CPP
    -0.07
    ä½ľè¯ģ
    -0.07
     agré
    -0.07
    æľī人说
    -0.07
    åı¯è§Ĥ
    -0.07
    aderos
    -0.07
    Investigators
    -0.07
    Imports
    -0.07
     messed
    -0.07
    POSITIVE LOGITS
    å°Ĭ
    0.07
    æĭ¬
    0.07
    uto
    0.07
    æĬ±æŃī
    0.06
    igon
    0.06
    æľªæŀľ
    0.06
    éĺģä¸ĭ
    0.06
    antd
    0.06
    åĩŃ
    0.06
    ry
    0.06
    Activations Density 0.043%

    No Known Activations