© 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. 21535
    Prev
    Next
    INDEX
    Explanations

    professional services

    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
     support
    -0.06
    常年
    -0.05
    åħij
    -0.05
    кло
    -0.05
     advise
    -0.05
    atics
    -0.05
    æĸ¯åĿ¦
    -0.05
    åĪĩçļĦ
    -0.05
    andard
    -0.05
    é¼ĵåĬ±
    -0.05
    POSITIVE LOGITS
    èĬ±èIJ½
    0.07
    ibbon
    0.06
    åĴĮèµĦæºIJ
    0.06
    çŁ¥ä¹ĭ
    0.06
    AMB
    0.05
    ey
    0.05
    witch
    0.05
    ä»»ãģĽ
    0.05
    åľ¨çĽ®
    0.05
    ç¿Ĵ
    0.05
    Activations Density 0.019%

    No Known Activations