© 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. 18768
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    unt
    -0.06
     nack
    -0.06
    indel
    -0.06
    mour
    -0.05
    edad
    -0.05
    mois
    -0.05
    born
    -0.05
    bable
    -0.05
    abbr
    -0.05
    ekl
    -0.05
    POSITIVE LOGITS
    æŃ¡è¿İ
    0.05
    æŀĦéĢł
    0.05
    ample
    0.05
    Ñģе
    0.05
    embra
    0.05
    åħħ足
    0.05
    OLID
    0.05
     general
    0.05
    åIJ¬å¾Ĺ
    0.05
    CompleteListener
    0.05
    Activations Density 0.000%

    No Known Activations