© 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. 20940
    Prev
    Next
    INDEX
    Explanations

    completion of cycles

    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
     r
    -0.06
    c
    -0.05
    mium
    -0.05
     C
    -0.05
     c
    -0.05
     D
    -0.05
     N
    -0.05
     R
    -0.05
     m
    -0.05
     d
    -0.05
    POSITIVE LOGITS
    Ä°K
    0.07
     perch
    0.07
     mene
    0.06
    ãĤ¢ãĥ³ãĥī
    0.06
    valo
    0.06
    人æīĭ
    0.06
    ”âĢ¦
    0.06
    ÑĢении
    0.06
    &p
    0.06
    кала
    0.06
    Activations Density 0.061%

    No Known Activations