© 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. 18213
    Prev
    Next
    INDEX
    Explanations

    synthetic materials

    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
    Expert
    -0.05
    Ùĩاد
    -0.05
     expert
    -0.05
    ated
    -0.05
    arity
    -0.05
    è±Ĩ
    -0.05
    driver
    -0.05
     o
    -0.05
    Lean
    -0.05
    Story
    -0.05
    POSITIVE LOGITS
    yron
    0.06
    idez
    0.06
    ä¸īåı£
    0.06
    åĪ°æĻļ
    0.06
    ienne
    0.06
    ÙĨدگاÙĨ
    0.06
    çĭ©
    0.06
    èĶ·
    0.06
    ordio
    0.06
    ób
    0.06
    Activations Density 0.001%

    No Known Activations