© 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. 16804
    Prev
    Next
    INDEX
    Explanations

    , followed by common verbs

    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
    bn
    -0.07
    lings
    -0.06
    ta
    -0.06
    annya
    -0.06
    ìĦł
    -0.06
    hr
    -0.06
    ount
    -0.05
    ib
    -0.05
     lem
    -0.05
    lets
    -0.05
    POSITIVE LOGITS
    inkin
    0.06
    ymmetric
    0.06
    ä¸Ĭè¿°äºĭå®ŀ
    0.06
     Bélgica
    0.06
     ìķŀëijIJê³ł
    0.06
     rembourse
    0.06
    *)"
    0.06
    ä¸Ńåħ·æľī
    0.06
    iago
    0.06
     Parall
    0.05
    Activations Density 0.115%

    No Known Activations