© 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. 22220
    Prev
    Next
    INDEX
    Explanations

    head of data structures, recursion, or classes

    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
    werk
    -0.06
    ãĥĩãĤ£ãĤª
    -0.06
     freedom
    -0.05
    åħ´
    -0.05
    former
    -0.05
     former
    -0.05
    Ñıви
    -0.05
    æīĢæĢĿ
    -0.05
    passen
    -0.05
    ulus
    -0.05
    POSITIVE LOGITS
     separ
    0.06
    à¹Ħม
    0.06
    าย
    0.06
    åĢĴ
    0.06
    åĪĨ离
    0.06
     corte
    0.06
    yse
    0.05
     separator
    0.05
     rispetto
    0.05
     dependen
    0.05
    Activations Density 0.017%

    No Known Activations