© 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. 20483
    Prev
    Next
    INDEX
    Explanations

    jedi, force, yoda, druid, ninja, master

    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
     sur
    -0.06
    -sized
    -0.05
     Sur
    -0.05
    ÑĤоÑĢаÑı
    -0.05
    头çĹĽ
    -0.05
    åįģä¸ī
    -0.05
    Ya
    -0.05
     god
    -0.05
    ewing
    -0.05
    yl
    -0.05
    POSITIVE LOGITS
    ondo
    0.06
    aan
    0.06
    -pad
    0.06
    feh
    0.06
    ãģĭãĤĭ
    0.06
    reed
    0.06
    alani
    0.06
    ways
    0.06
    eschi
    0.06
     corrup
    0.06
    Activations Density 0.001%

    No Known Activations