© 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. 17522
    Prev
    Next
    INDEX
    Explanations

    part ways, split off, separated

    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
    è±ļ
    -0.06
    ierto
    -0.05
     LOAD
    -0.05
    воÑİ
    -0.05
    å¼ĥ
    -0.05
     collect
    -0.05
    èĮĦ
    -0.05
     Sym
    -0.05
    æĸ¹åľĨ
    -0.05
     alternatively
    -0.05
    POSITIVE LOGITS
    åĪ«ç¦»
    0.06
     separated
    0.06
    سة
    0.06
    离åĪ«
    0.06
     ayr
    0.06
     separation
    0.06
    ·
    0.06
    utils
    0.06
     separ
    0.06
     seper
    0.06
    Activations Density 0.013%

    No Known Activations