© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 18867
    Prev
    Next
    INDEX
    Explanations

    union all or DISTRICT

    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
    åIJijèį£
    -0.08
     chá»ijt
    -0.06
    åŀĭ人æīį
    -0.06
    jÅ¡ÃŃ
    -0.06
    iode
    -0.06
    izacion
    -0.06
    tle
    -0.06
    irian
    -0.06
    åĦ¿çļĦ
    -0.06
    å°Ķåħĭ
    -0.06
    POSITIVE LOGITS
    oref
    0.05
    ¾
    0.05
    èĸĩèĸĩ
    0.05
    ås
    0.05
     Whilst
    0.05
    pip
    0.05
     DONE
    0.04
    å¸ĮæľĽ
    0.04
     consisting
    0.04
    管çIJĨ
    0.04
    Activations Density 0.002%

    No Known Activations