© 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. 21259
    Prev
    Next
    INDEX
    Explanations

    introduction

    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
    imiter
    -0.06
    igung
    -0.05
    ator
    -0.05
    eded
    -0.05
    ertime
    -0.05
    rend
    -0.05
    gin
    -0.05
    åĻ¨
    -0.05
    imus
    -0.05
    stw
    -0.05
    POSITIVE LOGITS
    åĨħ容æĺ¯
    0.06
    级åĪ«çļĦ
    0.06
    abar
    0.06
    åĨħ容ä¸İ
    0.05
    幸
    0.05
    ÚĨÙĩ
    0.05
    غÙĦ
    0.05
    oudre
    0.05
    ippo
    0.05
    esn
    0.05
    Activations Density 0.005%

    No Known Activations