© 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. 16715
    Prev
    Next
    INDEX
    Explanations

    tensor processing

    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
    )'),
    -0.07
     beze
    -0.07
    aisse
    -0.07
    åħĭæĸ¯
    -0.06
    ––
    -0.06
    ')</
    -0.06
    åıĮå±Ĥ
    -0.06
    retorno
    -0.06
    ,ep
    -0.06
    irin
    -0.06
    POSITIVE LOGITS
    ump
    0.05
     lump
    0.05
     shortened
    0.05
    ä¸Ģéĥ¨åĪĨ
    0.04
     dạng
    0.04
    um
    0.04
    C
    0.04
    ram
    0.04
     confession
    0.04
    èµ°ä¸ĬäºĨ
    0.04
    Activations Density 0.001%

    No Known Activations