© 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. 22431
    Prev
    Next
    INDEX
    Explanations

    ends of phrases or sentences

    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
    agen
    -0.06
     nues
    -0.06
    enza
    -0.06
    agy
    -0.05
    ur
    -0.05
    atson
    -0.05
    osz
    -0.05
    ait
    -0.05
    æ£ĭ
    -0.05
    eny
    -0.05
    POSITIVE LOGITS
    ulah
    0.06
     Führ
    0.05
    klus
    0.05
    oting
    0.05
     Freed
    0.05
    ảnh
    0.05
    uling
    0.05
    inol
    0.05
    çĶ¨æĪ·å¯¹
    0.05
    éĥ¨åĪĨç»ĦæĪIJ
    0.05
    Activations Density 0.001%

    No Known Activations