© 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. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 20986
    Prev
    Next
    INDEX
    Explanations

    life and death status

    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
     optim
    -0.06
    طاء
    -0.05
    imon
    -0.05
    åħijçİ°
    -0.05
     sincere
    -0.05
    url
    -0.05
    æĴ¤
    -0.05
    ff
    -0.05
     reverted
    -0.05
    jen
    -0.05
    POSITIVE LOGITS
    orable
    0.07
     escap
    0.06
     desar
    0.06
    æ´»
    0.06
    太éĥİ
    0.06
    alive
    0.06
    åģ¥åº·ä½ĵæ£Ģ
    0.06
    ãĥªãĥ¼ãĥ³
    0.06
    æĸ¯åŁº
    0.06
    软
    0.05
    Activations Density 0.039%

    No Known Activations