© 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. 17399
    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
     ala
    -0.06
     poput
    -0.06
    à¥Ģ
    -0.06
    urant
    -0.06
    orial
    -0.06
    zil
    -0.06
    atina
    -0.06
    ynth
    -0.06
    جÙħ
    -0.06
     Knob
    -0.05
    POSITIVE LOGITS
    APS
    0.06
    ábio
    0.06
    çĻ½çŁ³
    0.05
    ativ
    0.05
    念念
    0.05
    ÙĩÙħا
    0.05
    ms
    0.05
    æĺ
    0.05
    åĴĮåıijå±ķ
    0.05
    andra
    0.05
    Activations Density 0.000%

    No Known Activations