© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 20570
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     et
    -0.06
    heit
    -0.05
     Prime
    -0.05
    çķħ
    -0.05
    itr
    -0.05
    ↵
    -0.05
    ainment
    -0.05
    ,
    -0.04
    don
    -0.04
    ites
    -0.04
    POSITIVE LOGITS
    trait
    0.06
    åĴĮ对
    0.06
    æİĸ
    0.06
    å±ŀ
    0.06
    å½¹
    0.06
    ãģĶ缸è«ĩ
    0.06
    åĽŃè·¯
    0.06
    çĪĨäºĨ
    0.06
    pering
    0.06
    acca
    0.06
    Activations Density 0.000%

    No Known Activations