© 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. 18127
    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
    ãĤıãĤĬãģ«
    -0.07
    Ùĭ
    -0.07
     clubhouse
    -0.06
    oze
    -0.06
    æĪijæĥ³è¦ģ
    -0.06
    oriously
    -0.06
    indelijk
    -0.06
    åĬłæĭ¿å¤§
    -0.06
    loo
    -0.06
    losure
    -0.06
    POSITIVE LOGITS
    à¹ĩà¸ĩ
    0.05
     Firstly
    0.05
    es
    0.05
    urat
    0.05
    ist
    0.05
    isters
    0.05
    ray
    0.05
    ite
    0.05
     alt
    0.05
    ister
    0.05
    Activations Density 0.007%

    No Known Activations