© 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. 18067
    Prev
    Next
    INDEX
    Explanations

    complexity

    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
    ä¸Ģ身
    -0.06
    èī¯å¥½çļĦ
    -0.06
     اÙĦÙħر
    -0.05
    elis
    -0.05
    èī¯å¥½
    -0.05
    еÑĢж
    -0.05
    dach
    -0.05
     Weg
    -0.05
    %B
    -0.05
    ornings
    -0.05
    POSITIVE LOGITS
    robat
    0.06
    rev
    0.06
    à¸ĵà¸ij
    0.06
    ptes
    0.06
    ipas
    0.06
    genes
    0.06
    inki
    0.06
    cap
    0.06
    lave
    0.06
    dna
    0.06
    Activations Density 0.004%

    No Known Activations