© 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. 17532
    Prev
    Next
    INDEX
    Explanations

    programming declarations and types

    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
    ç³
    -0.07
    orat
    -0.06
    üy
    -0.06
    —including
    -0.06
    -yard
    -0.06
     involved
    -0.06
    å±±ä¹ĭ
    -0.06
    สำà¹Ģรà¹ĩà¸Ī
    -0.06
    ediat
    -0.06
    icias
    -0.06
    POSITIVE LOGITS
    xia
    0.05
    :
    0.05
     Rim
    0.05
     dear
    0.05
    讨好
    0.05
    æĹłæīĢè°ĵ
    0.05
    该åİ¿
    0.05
    åİ¿
    0.04
     References
    0.04
    lide
    0.04
    Activations Density 0.029%

    No Known Activations