© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 20294
    Prev
    Next
    INDEX
    Explanations

    business industry management services

    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
    راط
    -0.05
    Vision
    -0.05
     vision
    -0.05
     visions
    -0.05
    Ú
    -0.05
    cipher
    -0.05
     Brilliant
    -0.05
    als
    -0.05
    çļĦ人æĸĩ
    -0.05
    åłĤ
    -0.05
    POSITIVE LOGITS
     afer
    0.06
    FML
    0.06
     inherent
    0.06
    NZ
    0.06
     verk
    0.05
     inherently
    0.05
    ping
    0.05
    _utils
    0.05
     pes
    0.05
    inars
    0.05
    Activations Density 0.045%

    No Known Activations