© 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. 21465
    Prev
    Next
    INDEX
    Explanations

    white privilege, been comparing, national identity, verbally, ubiquitin

    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
    æĸ½
    -0.06
    åIJ¦
    -0.06
    æŃ£å¼ı
    -0.06
    å¼Ģ
    -0.06
    åį°
    -0.05
     softer
    -0.05
     shapes
    -0.05
    AMI
    -0.05
    å®ĺæĸ¹åįļ客
    -0.05
    à¹Ģà¸ĭ
    -0.05
    POSITIVE LOGITS
    èĮħ
    0.06
    aat
    0.06
     pal
    0.06
    íĻ©
    0.05
    fort
    0.05
    lebnis
    0.05
    è´¡çĮ®
    0.05
    åī§åľº
    0.05
     Sahara
    0.05
    ivel
    0.05
    Activations Density 0.011%

    No Known Activations