© 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. 22105
    Prev
    Next
    INDEX
    Explanations

    computing technology and systems

    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
    ation
    -0.12
    ı
    -0.07
    åĴĮè¦ģæ±Ĥ
    -0.06
    ed
    -0.06
    ATION
    -0.06
    rena
    -0.06
    æľīçĶŁ
    -0.06
    åıĬè¦ģæ±Ĥ
    -0.06
    ÃŃsticas
    -0.06
    mater
    -0.06
    POSITIVE LOGITS
    une
    0.07
    ersh
    0.06
    ÙĨد
    0.06
    ÙĨ
    0.06
    deaux
    0.06
    Õ¡Õ°
    0.06
    inde
    0.06
    place
    0.06
    ÙĬاء
    0.06
    à¸ģุ
    0.06
    Activations Density 0.006%

    No Known Activations