© 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. 17603
    Prev
    Next
    INDEX
    Explanations

    heuristic method

    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
     okazji
    -0.06
    master
    -0.06
     ensemble
    -0.06
    å·²éĢļè¿ĩ
    -0.06
    aes
    -0.06
     rame
    -0.06
    .si
    -0.06
    积æŀģåıĤä¸İ
    -0.05
    æŀģ端
    -0.05
    æŶéļĶ
    -0.05
    POSITIVE LOGITS
     descar
    0.06
     rational
    0.05
     recursion
    0.05
    leun
    0.05
    åĭ¢
    0.05
    çľ¼çľĭ
    0.05
    ubat
    0.05
     dez
    0.05
    å¾ģ
    0.05
    ulet
    0.05
    Activations Density 0.005%

    No Known Activations