© 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. 17589
    Prev
    Next
    INDEX
    Explanations

    reading or writing files

    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
    -0.05
     de
    -0.05
     AF
    -0.05
     post
    -0.05
     s
    -0.04
     a
    -0.04
     (
    -0.04
    åķĦ
    -0.04
     NO
    -0.04
    affen
    -0.04
    POSITIVE LOGITS
     contrac
    0.07
    Compiler
    0.07
     compilers
    0.07
     Compiler
    0.07
    rhein
    0.07
    æ´ĭ
    0.07
    ariate
    0.06
    ,map
    0.06
    ukai
    0.06
     sÃŃn
    0.06
    Activations Density 0.023%

    No Known Activations