© 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. 16758
    Prev
    Next
    INDEX
    Explanations

    Visual Studio .Net

    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
    æľīåħ¶ä»ĸ
    -0.05
    C
    -0.05
    ذب
    -0.05
     val
    -0.05
    尽管
    -0.05
    iname
    -0.05
     led
    -0.05
     il
    -0.04
    åı¦
    -0.04
    ä¾Ŀèµĸ
    -0.04
    POSITIVE LOGITS
    çĸĨ
    0.07
    ouv
    0.07
    Vars
    0.07
    eea
    0.06
     appartamenti
    0.06
    eneral
    0.06
     internals
    0.06
    UAR
    0.06
    /*/
    0.06
     artis
    0.06
    Activations Density 0.032%

    No Known Activations