© 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. 17049
    Prev
    Next
    INDEX
    Explanations

    coupe, footman, general aviation

    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
    ey
    -0.07
    åľ¨æĹģè¾¹
    -0.05
    outlined
    -0.05
    pluck
    -0.05
    oz
    -0.05
    ä»ĭç»įçļĦ
    -0.05
    å±İ
    -0.05
    åľ°ä¸ĬçļĦ
    -0.05
    迪
    -0.05
     Treat
    -0.05
    POSITIVE LOGITS
    ÑĤеа
    0.06
     ado
    0.06
     PMI
    0.05
    /libs
    0.05
    brig
    0.05
    çĶŁãģ¾
    0.05
    -book
    0.05
    Ł
    0.05
     volont
    0.05
    antics
    0.05
    Activations Density 0.044%

    No Known Activations