© 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. 22473
    Prev
    Next
    INDEX
    Explanations

    which

    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
    WK
    -0.07
     миÑĢ
    -0.06
    Ñĩин
    -0.06
    åĸľéĹ»ä¹IJ
    -0.06
    ercizio
    -0.06
    ombe
    -0.06
    ä¼įå¾·
    -0.06
    ä¼łåĩº
    -0.06
    íį¼
    -0.06
     prém
    -0.06
    POSITIVE LOGITS
    éĹ´çļĦ
    0.06
    å°Ĭ
    0.06
    å¿ĥ
    0.05
    ç¦ģ
    0.05
    èij«èĬ¦
    0.05
    à¸ķร
    0.05
     sole
    0.05
    iron
    0.05
    éĢĤ
    0.05
    åij¼
    0.05
    Activations Density 0.045%

    No Known Activations