© 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. 17018
    Prev
    Next
    INDEX
    Explanations

    positive adjectives of admiration

    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
    edar
    -0.06
    swick
    -0.06
     welcome
    -0.06
    agu
    -0.06
    ecem
    -0.06
     reminder
    -0.06
    encontre
    -0.06
    人åķĬ
    -0.06
    acen
    -0.06
    ordinate
    -0.06
    POSITIVE LOGITS
    еÑĢÑĮ
    0.07
    åıĹ人
    0.05
    ina
    0.05
    raje
    0.05
    γÏĮ
    0.05
    iva
    0.05
    anna
    0.05
     Nap
    0.05
    ä¸Ģçľ¼
    0.05
    adh
    0.05
    Activations Density 0.005%

    No Known Activations