© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 19905
    Prev
    Next
    INDEX
    Explanations

    chunks and splitting strings

    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
    éĽĨ
    -0.05
     commune
    -0.05
    lem
    -0.05
     راÛĮ
    -0.05
     intégré
    -0.05
    èħĶ
    -0.05
    çݯèĬĤ
    -0.05
    æŃ¥åħ¥
    -0.05
    iero
    -0.05
    inka
    -0.05
    POSITIVE LOGITS
    å®ŀéĻħæĵįä½ľ
    0.07
    åĪĩçļĦ
    0.06
     membag
    0.06
    utel
    0.06
     Generator
    0.06
    ç»ıèIJ¥ä¼ģä¸ļ
    0.06
    è¨ĪçĶ»
    0.06
     chunks
    0.06
    agger
    0.06
     approxim
    0.06
    Activations Density 0.021%

    No Known Activations