© 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. 17681
    Prev
    Next
    INDEX
    Explanations

    spacecraft crash

    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
    yster
    -0.06
    ieb
    -0.06
    åijIJ
    -0.05
    ondon
    -0.05
     palest
    -0.05
     symmetric
    -0.05
    åŃĺåĤ¨ç©ºéĹ´
    -0.05
     taught
    -0.05
     pictures
    -0.05
     balan
    -0.05
    POSITIVE LOGITS
    éĻįèIJ½
    0.06
    å¼Ĥçī©
    0.06
    дÑĢа
    0.06
    带åħ¥
    0.06
     stream
    0.05
    OUCH
    0.05
    åĨĻæ³ķ
    0.05
    .xaml
    0.05
    eming
    0.05
    åħ¥å¢ĥ
    0.05
    Activations Density 0.015%

    No Known Activations