© 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. 17568
    Prev
    Next
    INDEX
    Explanations

    file processing and data analysis

    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
     incontourn
    -0.06
    ÙĪÙĬد
    -0.06
     trouble
    -0.06
    æĸ°åĬłåĿ¡
    -0.06
    jo
    -0.06
    ekl
    -0.06
    eker
    -0.06
    паÑĢ
    -0.06
     muerto
    -0.06
    å¤ļ项
    -0.06
    POSITIVE LOGITS
    opes
    0.06
    ung
    0.05
     Herst
    0.05
    aldo
    0.05
    in
    0.05
    uper
    0.05
    Ci
    0.05
    ains
    0.05
    ific
    0.05
    ope
    0.04
    Activations Density 0.011%

    No Known Activations