© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 22398
    Prev
    Next
    INDEX
    Explanations

    list manipulation and substrings

    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
    Negative Logits
    å®ļæĢ§
    -0.05
    -0.05
    åı£
    -0.05
     (
    -0.05
    å®ļ
    -0.04
    ä¸įè¿ĩ
    -0.04
    å®ł
    -0.04
    สà¸ķ
    -0.04
    aat
    -0.04
     ale
    -0.04
    POSITIVE LOGITS
     **:**
    0.07
    zwi
    0.07
    zas
    0.06
    ensp
    0.06
     spree
    0.06
    ecten
    0.06
    apat
    0.06
    ãģ¾ãģŁãģ¯
    0.06
    ilitÃł
    0.06
    ussi
    0.06
    Activations Density 0.013%

    No Known Activations