© 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. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 22334
    Prev
    Next
    INDEX
    Explanations

    .exe files and code snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/qwen-3.5-saes/qwen-3.5-4b
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    äºĭäºĨ
    -0.05
    aks
    -0.05
    çݯå¢ĥå½±åĵį
    -0.05
    rot
    -0.05
    åĽłä¸ºæĪij们
    -0.05
     ge
    -0.04
    atta
    -0.04
    ç¸
    -0.04
    åŀ
    -0.04
    峡
    -0.04
    POSITIVE LOGITS
    æ·±åIJ¸
    0.06
    å½¼
    0.06
    çĶ¨äºİ
    0.06
    ilyn
    0.06
    eries
    0.06
    ëł¹
    0.06
    DEV
    0.06
    onex
    0.05
    ัà¹īà¸Ļ
    0.05
    æŀ£
    0.05
    Activations Density 0.005%

    No Known Activations