© 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. 20831
    Prev
    Next
    INDEX
    Explanations

    change 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
     change
    -0.06
    åıĺåĮĸ
    -0.06
    ÙĬات
    -0.06
    unch
    -0.06
     reun
    -0.05
    ÑĢиа
    -0.05
    æŃ£å¼ıä¸Ĭå¸Ĥ
    -0.05
     ($
    -0.05
     changes
    -0.05
    åıĺåĮĸçļĦ
    -0.05
    POSITIVE LOGITS
    eh
    0.07
    ez
    0.06
    é£Ł
    0.06
    éĻ¤
    0.06
    aux
    0.06
    zd
    0.06
    orge
    0.06
    ese
    0.06
    chu
    0.05
    itesse
    0.05
    Activations Density 0.021%

    No Known Activations