© 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. 21191
    Prev
    Next
    INDEX
    Explanations

    and

    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
    èĢĮè¨Ģä¹ĭ
    -0.06
    补贴æĶ¿çŃĸ
    -0.06
    åħļçļĦåįģä¹Ŀ大精ç¥ŀ
    -0.06
    werbung
    -0.06
    Añadir
    -0.06
    ingang
    -0.06
    ouston
    -0.06
     closely
    -0.06
     ÑĥÑģлÑĥгÑĥ
    -0.06
    elop
    -0.06
    POSITIVE LOGITS
    r
    0.05
    ore
    0.05
     S
    0.05
     denomin
    0.05
     se
    0.05
    _
    0.05
    åįļ
    0.05
    lds
    0.04
     d
    0.04
     per
    0.04
    Activations Density 0.100%

    No Known Activations