© 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. 16790
    Prev
    Next
    INDEX
    Explanations

    historical figures and events

    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
    -0.06
     resource
    -0.05
     State
    -0.05
    abel
    -0.05
     (
    -0.05
    iff
    -0.05
     E
    -0.05
     Chi
    -0.05
     bead
    -0.05
    ,
    -0.05
    POSITIVE LOGITS
     himself
    0.07
    OUCH
    0.07
    åIJĦè¡Į
    0.07
     Scalars
    0.07
    èĢĻ
    0.07
     lega
    0.07
    Scalars
    0.07
     Stéph
    0.06
     замеÑģÑĤи
    0.06
    vány
    0.06
    Activations Density 0.029%

    No Known Activations