© 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. 21268
    Prev
    Next
    INDEX
    Explanations

    to

    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
    ality
    -0.06
    èIJ¥
    -0.05
    aked
    -0.05
    keb
    -0.05
    ä¸ĭä¸Ģ
    -0.05
    acionamento
    -0.05
    аÑĢ
    -0.05
     accom
    -0.04
    omal
    -0.04
    pector
    -0.04
    POSITIVE LOGITS
    æĺ¾çĿĢ
    0.07
    大好
    0.06
    isos
    0.06
    mej
    0.06
    enne
    0.06
    课çļĦ
    0.06
    odia
    0.06
    esan
    0.06
    uille
    0.06
     sela
    0.06
    Activations Density 0.075%

    No Known Activations