© 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. 21664
    Prev
    Next
    INDEX
    Explanations

    github URLs and `.com` domains

    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
    à¹īา
    -0.06
    Å¡nj
    -0.06
     svens
    -0.06
     deliver
    -0.06
    edList
    -0.05
    Goal
    -0.05
    åĻ¨çļĦ
    -0.05
    deliver
    -0.05
     تÙĤد
    -0.05
    abbit
    -0.05
    POSITIVE LOGITS
     base
    0.07
    ateg
    0.06
    bases
    0.06
    åŁºæķ°
    0.06
     bases
    0.06
    ulg
    0.06
     Base
    0.06
    ffin
    0.06
    åŁºåľ°
    0.06
    åŁºç¡Ģ
    0.06
    Activations Density 0.005%

    No Known Activations