© 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. 17658
    Prev
    Next
    INDEX
    Explanations

    found/discovered + location

    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
    è¾ĵäºĨ
    -0.06
    å¾ĢæľŁç²¾å½©
    -0.06
    ivery
    -0.06
    avo
    -0.06
    足äºĨ
    -0.06
    ceeded
    -0.06
    otts
    -0.06
     Kudus
    -0.06
    åİ»äºĨ解
    -0.06
    æºIJçłģ
    -0.06
    POSITIVE LOGITS
    åıijçİ°çļĦ
    0.07
    åľ°åıijçİ°
    0.07
    çļĦåıijçİ°
    0.06
     khai
    0.05
    åıijçİ°äºĨ
    0.05
    åıijçİ°
    0.05
    迹
    0.05
    à¸Ĭิà¹īà¸Ļ
    0.05
    ugh
    0.05
     Happ
    0.05
    Activations Density 0.040%

    No Known Activations