© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 18074
    Prev
    Next
    INDEX
    Explanations

    curiosity about what

    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
    Not in Any Lists

    No Comments

    Negative Logits
    mut
    -0.06
    our
    -0.06
    amus
    -0.06
    åıijçİ°
    -0.05
    zend
    -0.05
    orris
    -0.05
    uyá»ĩt
    -0.05
    lern
    -0.05
    eur
    -0.05
     mini
    -0.05
    POSITIVE LOGITS
    çIJĨ论ä¸İå®ŀè·µ
    0.06
     smoother
    0.06
     pró
    0.06
    ua
    0.05
     studia
    0.05
     invers
    0.05
    สà¸Ļิà¸Ĺ
    0.05
    essore
    0.05
    为ä»Ģä¹Īä¼ļ
    0.05
    ç«Ńè¯ļ
    0.05
    Activations Density 0.007%

    No Known Activations