© 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. 22624
    Prev
    Next
    INDEX
    Explanations

    writingwriting boardwriting surface

    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
    空空
    -0.07
     ÙĦÙĦÙħرة
    -0.06
    æŃ¤èµ·
    -0.06
    oulos
    -0.06
    èĢĮå¤į
    -0.06
    åİŁåŀĭ
    -0.06
    ocs
    -0.06
    à¹Īวัà¸Ļ
    -0.06
     HOWEVER
    -0.05
    idis
    -0.05
    POSITIVE LOGITS
     cub
    0.06
    åĪ«
    0.06
    اء
    0.05
    ful
    0.05
    atio
    0.05
    ISTER
    0.05
     Ful
    0.05
    å½ĵä»ĸ们
    0.05
    horn
    0.05
    bindings
    0.05
    Activations Density 0.183%

    No Known Activations