© 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. 16844
    Prev
    Next
    INDEX
    Explanations

    conditional phrases or timing

    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
     nav
    -0.06
    p
    -0.06
    Made
    -0.06
    iless
    -0.06
    éĺ´
    -0.05
     Made
    -0.05
    ä½łå®¶
    -0.05
    bach
    -0.05
     нав
    -0.05
    icient
    -0.05
    POSITIVE LOGITS
     Nevertheless
    0.06
    ogh
    0.06
    å½ĵçĦ¶
    0.06
    ä¸įéģİ
    0.06
    å½ĵçĦ¶è¦ģ
    0.06
    æīĭåı¯
    0.06
    GEST
    0.06
    ç¼ĺ
    0.05
    ัà¸ĩ
    0.05
    ×Ĵר
    0.05
    Activations Density 0.155%

    No Known Activations