© 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. 16557
    Prev
    Next
    INDEX
    Explanations

    vocabulary and related contexts

    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
    转åħ¥
    -0.06
    uve
    -0.06
    avig
    -0.06
    rano
    -0.06
    ammu
    -0.06
    huizen
    -0.06
    bru
    -0.06
    orse
    -0.06
    amenta
    -0.06
     sebaliknya
    -0.06
    POSITIVE LOGITS
    anning
    0.06
    lore
    0.06
    æīĢ以å½ĵ
    0.06
    ä½į
    0.05
    á»ī
    0.05
    othe
    0.05
    ëį°
    0.05
    çĤ¹ç¼Ģ
    0.05
     Strand
    0.05
    strand
    0.05
    Activations Density 0.002%

    No Known Activations