© 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. 20799
    Prev
    Next
    INDEX
    Explanations

    were

    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
    icans
    -0.07
    imoni
    -0.06
    gegen
    -0.06
    ünd
    -0.06
    æĬµæī£
    -0.06
    mati
    -0.06
    åĵij
    -0.06
    eway
    -0.06
    -lite
    -0.06
     acu
    -0.06
    POSITIVE LOGITS
    eny
    0.08
    å±ŀäºİ
    0.06
    ammel
    0.05
    vole
    0.05
    è¦ģä¹Īæĺ¯
    0.05
     Post
    0.05
    ÌĢ
    0.05
    ucker
    0.05
    ouw
    0.05
    Post
    0.05
    Activations Density 0.157%

    No Known Activations