© 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. 19803
    Prev
    Next
    INDEX
    Explanations

    combinations, configurations, conditions, groups

    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
    arco
    -0.07
    vang
    -0.07
    iciels
    -0.06
    depth
    -0.06
    éĻĦ带
    -0.06
    侧
    -0.06
     concre
    -0.06
    integrazione
    -0.06
    åįļæł¼
    -0.06
    amani
    -0.06
    POSITIVE LOGITS
     combinations
    0.08
     combina
    0.07
     combination
    0.06
     combine
    0.06
    شر
    0.06
    led
    0.06
     combos
    0.05
    æħ¾
    0.05
     class
    0.05
    Comb
    0.05
    Activations Density 0.081%

    No Known Activations