© 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. 17310
    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
    elic
    -0.05
    unter
    -0.05
    tick
    -0.05
    èݱæĸ¯
    -0.05
    anner
    -0.05
    æ²ŁæĿij
    -0.05
    éĴ¦
    -0.05
    SES
    -0.05
    å¯ĵ
    -0.05
    angelo
    -0.05
    POSITIVE LOGITS
    estring
    0.06
    Ñģловно
    0.06
    Ùģا
    0.05
    ENTES
    0.05
    stry
    0.05
     multim
    0.05
     interf
    0.05
     Ñģоп
    0.05
    inston
    0.05
    æħ
    0.05
    Activations Density 0.000%

    No Known Activations